© 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. 54001
    Prev
    Next
    INDEX
    Explanations

    Australian drama series media

    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
     Snake
    -0.09
    .Man
    -0.09
    usta
    -0.08
    ivic
    -0.08
    onen
    -0.08
    ç»ĵæŀĦè°ĥæķ´
    -0.08
    éŁŃ
    -0.08
     bitch
    -0.08
    olley
    -0.08
    ividual
    -0.08
    POSITIVE LOGITS
    åĦ¿ç«¥
    0.22
    ç«¥è¯Ŀ
    0.17
    åŃ©åŃIJ们
    0.17
    åŃ©åŃIJçļĦ
    0.17
     children
    0.16
    迪士尼
    0.16
    åį¡éĢļ
    0.16
    åħĴç«¥
    0.16
    åŃ©åŃIJ
    0.15
    çļĦåŃ©åŃIJ
    0.15
    Activations Density 0.200%

    No Known Activations