© 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. 24080
    Prev
    Next
    INDEX
    Explanations

    System

    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
    (".")
    -0.08
     Foods
    -0.08
     Stops
    -0.08
    ween
    -0.07
    柳
    -0.07
    uD
    -0.07
     Roulette
    -0.07
     ohne
    -0.07
    ulses
    -0.07
    thouse
    -0.07
    POSITIVE LOGITS
     üretim
    0.06
    _eff
    0.06
    CI
    0.06
    (id
    0.06
     cancell
    0.06
    rik
    0.06
     reflecting
    0.06
    avelength
    0.06
    一体化
    0.06
    owner
    0.06
    Activations Density 0.001%

    No Known Activations