© 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. 49203
    Prev
    Next
    INDEX
    Explanations

    whim or whining

    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
    ivalence
    -0.10
    adox
    -0.08
    unner
    -0.08
    _rsp
    -0.08
    .GetValue
    -0.08
    sembles
    -0.08
     пÑĢименениÑı
    -0.08
    imeo
    -0.08
    urgeon
    -0.08
    è§Ī
    -0.08
    POSITIVE LOGITS
    çīĩåŃIJ
    0.11
    pery
    0.11
    kowski
    0.10
    èĦį
    0.10
    åı£æ°Ķ
    0.09
    åĦ¿
    0.09
    uet
    0.09
    ãģĤãģ£ãģ¦
    0.09
    è½²
    0.09
    ppers
    0.09
    Activations Density 0.004%

    No Known Activations