© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38168
    Prev
    Next
    INDEX
    Explanations

    Eclipse, Ghost, Zurich, Player licenses

    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
    acha
    -0.09
     instincts
    -0.09
    è¿ĺ以为
    -0.09
    otta
    -0.08
    icked
    -0.08
    clar
    -0.08
    ester
    -0.08
    ase
    -0.08
    åĽ´è§Ĥ
    -0.08
    lem
    -0.08
    POSITIVE LOGITS
    /disable
    0.14
     dÃłng
    0.11
    ablish
    0.11
    uating
    0.10
    -disable
    0.10
    ä½ļ
    0.10
     coli
    0.10
    ILON
    0.09
    ipse
    0.09
    IRONMENT
    0.09
    Activations Density 0.839%

    No Known Activations