© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 23785
    Prev
    Next
    INDEX
    Explanations

    _INLINE, L

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >List
    -0.07
     Trên
    -0.06
    guild
    -0.06
    icultural
    -0.06
    安卓
    -0.06
    第一百
    -0.06
    éments
    -0.06
    implified
    -0.06
    вест
    -0.06
     prepared
    -0.06
    POSITIVE LOGITS
     Logo
    0.08
     fluctuations
    0.07
    ᄄ
    0.07
     Netherlands
    0.07
     shoes
    0.07
     Weather
    0.07
     Forms
    0.07
     Tech
    0.07
     dismantle
    0.06
     acne
    0.06
    Activations Density 0.001%

    No Known Activations