© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47965
    Prev
    Next
    INDEX
    Explanations

    entrance hall

    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
    aceous
    -0.13
    tron
    -0.13
    ãĥ¼ãĤ¹
    -0.11
    å¢ŀè¿Ľ
    -0.10
    Ń
    -0.10
    ī
    -0.10
    åĹĵåŃIJ
    -0.10
    åŃIJéĩĮ
    -0.09
    å²ĺ
    -0.09
    ç½´
    -0.09
    POSITIVE LOGITS
    prising
    0.09
    iveness
    0.09
    prises
    0.09
    idis
    0.08
    nin
    0.08
    adio
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    pects
    0.08
    ull
    0.08
    ability
    0.08
    Activations Density 0.007%

    No Known Activations