© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60859
    Prev
    Next
    INDEX
    Explanations

    Black Rock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anged
    -0.11
    ảng
    -0.10
    aget
    -0.09
    ulong
    -0.09
    MENT
    -0.09
    ally
    -0.09
    chter
    -0.09
    ר×Ķ
    -0.09
    kins
    -0.09
    ange
    -0.09
    POSITIVE LOGITS
    ened
    0.19
    ness
    0.14
    ish
    0.12
    ening
    0.12
    smith
    0.12
    listed
    0.12
    most
    0.11
    ãģªãĤīãģªãģĦ
    0.11
    nowled
    0.10
    pile
    0.10
    Activations Density 0.043%

    No Known Activations