© 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. 7-RESID-POST-AA
    11. 8453
    Prev
    Next
    INDEX
    Explanations

    Public

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inia
    -0.07
    דרוש
    -0.07
    führer
    -0.07
    oriasis
    -0.07
     Fra
    -0.07
    wią
    -0.07
    Inc
    -0.07
    กำหนด
    -0.06
     Encore
    -0.06
    tones
    -0.06
    POSITIVE LOGITS
     inequality
    0.07
    elled
    0.06
    常德
    0.06
    ty
    0.06
     closed
    0.06
     �
    0.06
    sted
    0.06
     reflex
    0.06
    Retry
    0.06
     Payload
    0.06
    Activations Density 0.001%

    No Known Activations