© 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. 5221
    Prev
    Next
    INDEX
    Explanations

    computing, investing, recruiting, observing

    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
    ary
    -0.12
    åħĭæĸ¯
    -0.09
    pak
    -0.09
    бÑĢ
    -0.08
    agog
    -0.08
    VEN
    -0.08
    pered
    -0.08
    /or
    -0.08
    creasing
    -0.08
    aley
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.11
    uild
    0.09
    uilt
    0.09
    erview
    0.08
    ullen
    0.08
    åŃ¢
    0.08
    éķĢéĶĮ
    0.08
    ound
    0.08
    ewise
    0.08
    ÈĽi
    0.08
    Activations Density 0.078%

    No Known Activations