© 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. 11-RESID-POST-AA
    11. 56986
    Prev
    Next
    INDEX
    Explanations

    born with

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     HBO
    -0.08
    掭
    -0.07
    mouseup
    -0.07
    حج
    -0.07
    öğret
    -0.07
    舀
    -0.07
    tors
    -0.07
     número
    -0.07
     numel
    -0.07
    animation
    -0.07
    POSITIVE LOGITS
    �
    0.08
    很简单
    0.07
     مختلفة
    0.07
    itious
    0.07
    彬
    0.07
     Fiesta
    0.07
    废弃物
    0.07
    ::::
    0.07
    :black
    0.07
    0.07
    Activations Density 0.023%

    No Known Activations