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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14996
    Prev
    Next
    INDEX
    Explanations

    RPG

    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
     chassis
    -0.08
    线上线下
    -0.07
    <|im_end|>
    -0.07
     destinations
    -0.07
    [List
    -0.07
     встреча
    -0.07
    (NUM
    -0.07
    -Clause
    -0.07
    >Delete
    -0.07
    ))/(
    -0.07
    POSITIVE LOGITS
     chịu
    0.09
    פגיעה
    0.08
     winger
    0.08
    ⊗
    0.07
     derecho
    0.07
     Milky
    0.07
    Polygon
    0.07
     angrily
    0.07
    تأثير
    0.07
    عن
    0.07
    Activations Density 0.003%

    No Known Activations