© 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. 107571
    Prev
    Next
    INDEX
    Explanations

    correction or disagreement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Compilation
    -0.07
     distress
    -0.07
     Linux
    -0.07
    .so
    -0.07
    (mutex
    -0.07
     mixing
    -0.07
     Since
    -0.06
    ？”
    -0.06
    Since
    -0.06
    nea
    -0.06
    POSITIVE LOGITS
     CONNECTION
    0.07
    沿途
    0.07
    ਰ
    0.07
     그것
    0.06
     inherently
    0.06
    .maps
    0.06
    俞
    0.06
    стро
    0.06
    (END
    0.06
     PARK
    0.06
    Activations Density 0.060%

    No Known Activations