© 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. 1287
    Prev
    Next
    INDEX
    Explanations

    caravan / convoy / travel groups

    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
    ãĤ¢ãĥĬ
    -0.09
    çĿĽ
    -0.09
    tmpl
    -0.09
    çı²
    -0.09
    errupt
    -0.09
    Ĥæķ°
    -0.09
    ì²Ń
    -0.09
    cess
    -0.09
    LESS
    -0.09
    UND
    -0.08
    POSITIVE LOGITS
    nier
    0.11
    ../../../
    0.10
    ï¸
    0.09
    atic
    0.09
    edly
    0.09
    ç¾Ķ
    0.08
     sá»ķ
    0.08
    éĿĻ
    0.08
    ÙĬÙĬÙĨ
    0.08
     ÙĪاÙĦاست
    0.08
    Activations Density 0.003%

    No Known Activations