© 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. 4525
    Prev
    Next
    INDEX
    Explanations

    eating and biting

    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
    emotion
    -0.10
    rawn
    -0.10
    饮çĶ¨æ°´
    -0.09
    atos
    -0.09
    urus
    -0.08
    raft
    -0.08
    atem
    -0.08
    илоÑģÑĮ
    -0.08
    anvas
    -0.08
    lagen
    -0.08
    POSITIVE LOGITS
    èµİ
    0.10
    çĽĴ
    0.09
    åѦçĶŁä»¬
    0.09
    èķ
    0.08
    åĮ®
    0.08
    semble
    0.08
    ToEnd
    0.08
    è¿Ľåİ»
    0.08
    ä¸Ĭå¸Ĥ
    0.08
    /sn
    0.08
    Activations Density 0.008%

    No Known Activations