© 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. 35169
    Prev
    Next
    INDEX
    Explanations

    eyes closed or dark

    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
    çIJĽ
    -0.10
    æĭĸ
    -0.09
    drag
    -0.09
    æ¶ĪçģŃ
    -0.09
    acid
    -0.09
    keh
    -0.09
     Drag
    -0.09
    æ¸ħéĨĴ
    -0.08
    artic
    -0.08
    Ø°Ùĩ
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īéĥ½
    0.12
    çľĭä¸įåĪ°
    0.11
    èĽŁ
    0.10
    æ¿Ģæĥħ
    0.10
    ä¸įæ¸ħæ¥ļ
    0.10
    çĽ²
    0.09
    /bl
    0.09
    ä¸įæ¸ħ
    0.09
    æĪijä¸įçŁ¥éģĵ
    0.09
    åĤħ
    0.09
    Activations Density 0.037%

    No Known Activations