© 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. 35273
    Prev
    Next
    INDEX
    Explanations

    treated with dignity or care

    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
    è¢ĸ
    -0.11
    anian
    -0.11
    ç®Ĺ
    -0.10
    å±ķæ¼Ķ
    -0.10
    åħĭæľį
    -0.09
    kest
    -0.09
    à¹ģà¸ģ
    -0.09
    ignon
    -0.09
     CLUB
    -0.09
     Guill
    -0.09
    POSITIVE LOGITS
    éĩįè§Ĩ
    0.10
    对å¾ħ
    0.10
    å°Ĭéĩį
    0.10
    çIJĨ解åĴĮ
    0.08
     importance
    0.08
    褶
    0.08
    æł¼å¤ĸ
    0.08
    棨
    0.08
    Fra
    0.08
    subs
    0.08
    Activations Density 0.040%

    No Known Activations