© 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. 32954
    Prev
    Next
    INDEX
    Explanations

    say " marks"

    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
    Alt
    -0.08
    .minimum
    -0.07
    🇺
    -0.07
    .rotate
    -0.07
    Alternatively
    -0.07
    Voice
    -0.07
    .BackgroundImageLayout
    -0.07
    enerative
    -0.07
    Common
    -0.07
     handwritten
    -0.07
    POSITIVE LOGITS
     headline
    0.07
     декаб
    0.07
     disclose
    0.07
     treats
    0.07
    要求
    0.07
    ителей
    0.07
    咯
    0.07
     Classifier
    0.07
     increases
    0.07
    疯
    0.06
    Activations Density 0.002%

    No Known Activations