© 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. 37724
    Prev
    Next
    INDEX
    Explanations

    limb supports or salvage

    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
    ----------------------------------------------------------------
    -0.09
    hips
    -0.09
    enal
    -0.09
    itionally
    -0.09
    常å§Ķ
    -0.09
    èµĢ
    -0.09
    æĤ£
    -0.09
    specified
    -0.09
    èĪIJ
    -0.08
    esco
    -0.08
    POSITIVE LOGITS
    lessly
    0.11
    elight
    0.10
    atic
    0.10
    atics
    0.09
    Ø«
    0.09
    ANCH
    0.09
    acity
    0.09
    åĪĨæĺİ
    0.09
    azon
    0.09
    зн
    0.09
    Activations Density 0.078%

    No Known Activations