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. 11-RESID-POST-AA
    6. 87231
    Prev
    Next
    INDEX
    Explanations

    transistors and circuits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :ss
    -0.08
    シェ
    -0.07
     Distribution
    -0.07
     nelle
    -0.07
    תחילת
    -0.07
    可持续
    -0.07
    סטוד
    -0.07
    -J
    -0.07
    沙滩
    -0.07
    涅
    -0.07
    POSITIVE LOGITS
     אליה
    0.07
     mut
    0.07
     noun
    0.07
     Drum
    0.07
    ⟫
    0.07
    _xyz
    0.07
    栝
    0.07
     PHP
    0.06
    ppy
    0.06
    別人
    0.06
    Activations Density 0.020%

    No Known Activations