© 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. 17326
    Prev
    Next
    INDEX
    Explanations

    fiction/narrative

    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
    شا
    -0.08
    elib
    -0.07
    צא
    -0.07
    ティ
    -0.07
    fully
    -0.07
    şi
    -0.06
    身
    -0.06
     criticize
    -0.06
    palette
    -0.06
    spy
    -0.06
    POSITIVE LOGITS
    :NSMakeRange
    0.08
     Permissions
    0.07
     Preparation
    0.07
     aprend
    0.07
    ivated
    0.07
     induced
    0.06
    -br
    0.06
     enhanced
    0.06
     "**
    0.06
     woll
    0.06
    Activations Density 0.065%

    No Known Activations