© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18726
    Prev
    Next
    INDEX
    Explanations

    randomized

    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
    Negative Logits
    🚕
    -0.07
    🆙
    -0.07
    ╃
    -0.07
     dependency
    -0.07
    这才
    -0.07
    这让
    -0.06
     Unreal
    -0.06
    -review
    -0.06
    ickey
    -0.06
    \V
    -0.06
    POSITIVE LOGITS
    ورد
    0.06
    座椅
    0.06
    Helmet
    0.06
    stick
    0.06
    _OC
    0.06
    被捕
    0.06
    push
    0.06
    /Desktop
    0.06
    трад
    0.06
    海滩
    0.06
    Activations Density 0.004%

    No Known Activations