© 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. 19-RESID-POST-AA
    11. 70932
    Prev
    Next
    INDEX
    Explanations

    com

    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
    高效的
    -0.07
     Ecc
    -0.07
     exercising
    -0.06
     devices
    -0.06
     engulf
    -0.06
    Mesh
    -0.06
    全新的
    -0.06
    غاز
    -0.06
    在他
    -0.06
    anne
    -0.06
    POSITIVE LOGITS
    stderr
    0.07
    YPRE
    0.07
    ┎
    0.07
    -spec
    0.07
    	placeholder
    0.07
    jury
    0.07
    莅
    0.07
    롑
    0.07
     retries
    0.07
    更多精彩
    0.06
    Activations Density 0.004%

    No Known Activations