© 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. 54976
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    壹
    -0.11
    plib
    -0.10
    åı¦å¤ĸä¸Ģ个
    -0.10
    åı¦ä¸Ģç§į
    -0.10
    åı¦ä¸Ģ个
    -0.10
    è°
    -0.09
    çݩ家们
    -0.09
    çĹĤ
    -0.09
    ä¹İ
    -0.09
    ä¸ĥ大
    -0.09
    POSITIVE LOGITS
    çĹħæĥħ
    0.09
    oz
    0.09
     Dee
    0.09
    vote
    0.09
    说èĩªå·±
    0.09
    Drag
    0.08
    åıĽ
    0.08
    votes
    0.08
    NSE
    0.08
     condition
    0.08
    Activations Density 0.074%

    No Known Activations