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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 2914
    Prev
    Next
    INDEX
    Explanations

    structure

    np_max-act-logits · gemini-2.0-flash
    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
    严格执行
    -0.08
     Kul
    -0.07
     November
    -0.07
    everything
    -0.07
     --------------------------------------------------------------------------↵
    -0.07
    -yyyy
    -0.07
     mattresses
    -0.07
     יהיה
    -0.06
     jewelry
    -0.06
     אחד
    -0.06
    POSITIVE LOGITS
    goal
    0.07
    Gap
    0.07
     planta
    0.07
     onStart
    0.07
    MethodManager
    0.07
    [W
    0.07
    .onError
    0.07
    Prompt
    0.07
     textarea
    0.07
    tra
    0.06
    Activations Density 0.189%

    No Known Activations