© 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. 7641
    Prev
    Next
    INDEX
    Explanations

    code/mathematics expressions

    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
     Darth
    -0.08
    追究
    -0.07
    Nombre
    -0.06
     pervasive
    -0.06
    蹚
    -0.06
     Europa
    -0.06
    あなたの
    -0.06
    TransparentColor
    -0.06
     Springer
    -0.06
     racism
    -0.06
    POSITIVE LOGITS
    썼
    0.07
    来た
    0.07
    closed
    0.07
     adamant
    0.07
    rtype
    0.07
    였
    0.07
    .Ex
    0.07
    +s
    0.07
    满意的
    0.07
    _HASH
    0.07
    Activations Density 0.001%

    No Known Activations