© 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. 19-RESID-POST-AA
    11. 59834
    Prev
    Next
    INDEX
    Explanations

    say the ending -ations

    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
    Negative Logits
    charg
    -0.08
     kapı
    -0.07
    二次
    -0.07
    (pointer
    -0.07
     граждан
    -0.07
     mạch
    -0.06
    .cross
    -0.06
    =("
    -0.06
     ידי
    -0.06
     stratég
    -0.06
    POSITIVE LOGITS
                                                ↵
    0.07
    稳定
    0.07
     #↵
    0.07
    **
    0.07
    Elite
    0.07
    +'&
    0.07
    開展
    0.07
    展演
    0.07
    進行
    0.07
    系統
    0.07
    Activations Density 0.003%

    No Known Activations