© 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. 37272
    Prev
    Next
    INDEX
    Explanations

    .org / .net domains

    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
    lds
    -0.10
    çĶ¨æ°´
    -0.09
     Extension
    -0.09
    课åłĤæķĻåѦ
    -0.09
    Extension
    -0.09
    line
    -0.09
    force
    -0.09
    .Extension
    -0.08
    laus
    -0.08
    è¾Ī
    -0.08
    POSITIVE LOGITS
    à¸Ĥา
    0.10
    inka
    0.09
    onné
    0.09
    çIJĨæĻº
    0.09
    ä¸Ģ缴åĪ°
    0.09
    å¿«é¤IJ
    0.09
    -fw
    0.09
    æ¯ħçĦ¶
    0.09
    ethylene
    0.09
    _TRANSL
    0.09
    Activations Density 0.027%

    No Known Activations