Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 8469
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash

    clause-separating punctuation, especially commas and dashes within sentences and dialogue.

    oai_token-act-pair · gpt-5Triggered by @jdhshshs138
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Classe
    -0.08
    (ActionEvent
    -0.08
    hores
    -0.07
    (ALOAD
    -0.07
    chte
    -0.07
    גוד
    -0.07
     entities
    -0.07
    _charset
    -0.07
    .chdir
    -0.07
     propelled
    -0.07
    POSITIVE LOGITS
    升
    0.07
     Browse
    0.07
     PWM
    0.07
    牧
    0.07
    >.
    0.07
    ✫
    0.07
    档案
    0.06
    反映了
    0.06
    🌕
    0.06
    森林
    0.06
    Activations Density 0.071%

    No Known Activations