© 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. 33703
    Prev
    Next
    INDEX
    Explanations

    pump

    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
    çĤ¬
    -0.09
    åī¡
    -0.09
    è®·
    -0.09
    INGS
    -0.09
    çĻ¾èĬ±
    -0.09
    çijĻ
    -0.09
     lã
    -0.09
    ieber
    -0.09
     trickle
    -0.08
    ç³Ļ
    -0.08
    POSITIVE LOGITS
     suspend
    0.09
    容å¿į
    0.09
     pumping
    0.09
    æīĵåħ¥
    0.09
    asers
    0.09
    wr
    0.08
    æĿ²
    0.08
    Separated
    0.08
    å¸
    0.08
    UNS
    0.08
    Activations Density 0.009%

    No Known Activations