© 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. 32300
    Prev
    Next
    INDEX
    Explanations

    high-speed communication and transmission

    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
    å¸ģ
    -0.11
    RELATED
    -0.10
     nou
    -0.09
    teen
    -0.09
    è¡·
    -0.09
    åį¦
    -0.09
    åij³éģĵ
    -0.08
    ISTA
    -0.08
    åı¥è¯Ŀ
    -0.08
    è¿Łè¿Ł
    -0.08
    POSITIVE LOGITS
    ingly
    0.10
    lement
    0.10
     pyl
    0.09
    uron
    0.09
     мало
    0.09
     Wick
    0.09
    urious
    0.08
    atic
    0.08
    ä½Ĩä»į
    0.08
    igm
    0.08
    Activations Density 0.054%

    No Known Activations