© 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. 120391
    Prev
    Next
    INDEX
    Explanations

    HTTP protocol versions

    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
     dull
    -0.07
     Waves
    -0.07
    Sign
    -0.07
     Key
    -0.07
     ppt
    -0.07
     overlays
    -0.06
    relay
    -0.06
     lay
    -0.06
     הבלוג
    -0.06
     aggregator
    -0.06
    POSITIVE LOGITS
    wanted
    0.07
    חשבתי
    0.07
     donc
    0.07
    bery
    0.07
    חול
    0.07
    cwd
    0.07
     выпол
    0.07
    خطط
    0.07
    -F
    0.07
     Método
    0.07
    Activations Density 0.008%

    No Known Activations