© 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. 6958
    Prev
    Next
    INDEX
    Explanations

    van } name } prefix

    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
    ceso
    -0.11
    imos
    -0.09
    åıªéľĢè¦ģ
    -0.09
    èĪ±
    -0.09
    PLICIT
    -0.09
    /loader
    -0.09
    raphics
    -0.09
    -gnu
    -0.09
    æĸ¯åŁº
    -0.09
    .Nav
    -0.09
    POSITIVE LOGITS
    çĶ«
    0.09
    尽快
    0.09
    ä¸Ģ个éĩįè¦ģ
    0.09
    in
    0.08
    ä¸Ģæĸ¹
    0.08
    å®ģ
    0.08
    oven
    0.08
     ÑĩиÑģл
    0.08
    äºļåĨĽ
    0.08
    æĥ³çĿĢ
    0.08
    Activations Density 0.034%

    No Known Activations