© 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. 22140
    Prev
    Next
    INDEX
    Explanations

    server

    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
    æĦŁ
    -0.11
    .stride
    -0.10
    fork
    -0.10
    å°º
    -0.10
    incipal
    -0.09
    å²Ń
    -0.09
    æ¶ī足
    -0.09
    éŀŃ
    -0.09
    osti
    -0.09
    æįĤ
    -0.09
    POSITIVE LOGITS
    æľįåĬ¡åĻ¨
    0.21
     servers
    0.19
     server
    0.17
     ÑģеÑĢвеÑĢ
    0.15
    .getServer
    0.14
    servers
    0.13
     Servers
    0.13
    ãĤµãĥ¼ãĥ
    0.13
    server
    0.13
    .SERVER
    0.12
    Activations Density 0.293%

    No Known Activations