© 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. 83007
    Prev
    Next
    INDEX
    Explanations

    use

    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
    ADR
    -0.08
     vä
    -0.07
     Southern
    -0.07
    enne
    -0.07
    Mil
    -0.07
    爱护
    -0.07
    协会会长
    -0.07
     Xiao
    -0.07
    חד
    -0.06
    izzly
    -0.06
    POSITIVE LOGITS
    镘
    0.07
    -grow
    0.07
    History
    0.07
     kém
    0.07
     כת
    0.06
     осуществ
    0.06
    组织实施
    0.06
    功能
    0.06
     whence
    0.06
     ambit
    0.06
    Activations Density 0.055%

    No Known Activations