© 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. 54765
    Prev
    Next
    INDEX
    Explanations

    explosive cord, HIC

    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§ī
    -0.09
    vig
    -0.09
     fe
    -0.09
    asia
    -0.08
    åĽ¢
    -0.08
    ä¼Ł
    -0.08
    åŃ©
    -0.08
    .gs
    -0.08
    红è±Ĩ
    -0.08
     Engl
    -0.08
    POSITIVE LOGITS
    å¼¹
    0.12
    åĩ»
    0.11
    åĨ²åĩ»
    0.10
    ç²¾èĩ´
    0.09
     muzzle
    0.09
    ç²īç¢İ
    0.09
    èĩ»
    0.09
     blast
    0.09
    以åħ¶
    0.09
     ÑĥдаÑĢ
    0.09
    Activations Density 0.141%

    No Known Activations