© 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. 18161
    Prev
    Next
    INDEX
    Explanations

    franchise/school/club history

    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
    åħ¶æīĢ
    -0.12
    ulling
    -0.08
    åIJĦåľ°
    -0.08
     Complete
    -0.08
    æĸŃ
    -0.08
    åħį
    -0.08
    ijľ
    -0.07
    éĢīæīĭ
    -0.07
    Knight
    -0.07
    åĬ²
    -0.07
    POSITIVE LOGITS
    åİĨåı²ä¸Ĭ
    0.14
    åİĨåı²
    0.12
    åİĨåı²æĸ°
    0.12
    åı²ä¸Ĭ
    0.10
    çļĦåİĨåı²
    0.10
    åı²ä¸ĬæľĢ
    0.10
    çķĻä¸ĭäºĨ
    0.10
    æŃ·åı²
    0.10
    è¡ĢèĦī
    0.09
    å©¢
    0.09
    Activations Density 0.010%

    No Known Activations