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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 121463
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Marvin
    -0.07
     start
    -0.07
    ㄹ
    -0.07
     animal
    -0.07
     groom
    -0.07
     findings
    -0.07
     delete
    -0.07
    ﾚ
    -0.07
    中小学
    -0.07
    ISR
    -0.07
    POSITIVE LOGITS
     Works
    0.07
    시스
    0.07
     общ
    0.07
    얽
    0.07
    SetFont
    0.06
     Чт
    0.06
    تور
    0.06
    (company
    0.06
    -support
    0.06
    tection
    0.06
    Activations Density 0.158%

    No Known Activations