© 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. 52898
    Prev
    Next
    INDEX
    Explanations

    miscellaneous or misc items

    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
    isoft
    -0.10
    楮
    -0.09
    nown
    -0.09
    rende
    -0.09
    iks
    -0.09
    /or
    -0.08
    èĥ¨
    -0.08
    å®Ľ
    -0.08
    è®°å¿ĨåĬĽ
    -0.08
    tail
    -0.08
    POSITIVE LOGITS
    ellaneous
    0.21
    æĿĤ
    0.12
    -purpose
    0.12
    ellan
    0.11
    misc
    0.11
    éĽ
    0.10
    .Misc
    0.10
     Misc
    0.09
    åħ¶å®ĥ
    0.09
    lei
    0.09
    Activations Density 0.013%

    No Known Activations