© 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. 48477
    Prev
    Next
    INDEX
    Explanations

    pounce, dart, jump

    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
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.11
    æµĬ
    -0.11
    ä¸ĢæŃ¥æŃ¥
    -0.10
    çĸı
    -0.10
    å¾ĺå¾Ĭ
    -0.10
    èī¯
    -0.09
    ISK
    -0.09
    éĵ¢
    -0.09
    没æľīåĬŀæ³ķ
    -0.09
    <Scalar
    -0.09
    POSITIVE LOGITS
    æĺĻ
    0.11
     dart
    0.11
    è·³è·ĥ
    0.11
     surprise
    0.10
    çªģçĦ¶
    0.10
    çªģ
    0.08
    è¢Ńåĩ»
    0.08
    .amazonaws
    0.08
    éĶIJ
    0.08
    jump
    0.08
    Activations Density 0.076%

    No Known Activations