© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51534
    Prev
    Next
    INDEX
    Explanations

    police

    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
    ists
    -0.10
    èĢģ人家
    -0.10
    ate
    -0.10
    abouts
    -0.09
    sWith
    -0.09
    åĦ¿
    -0.09
    éĢıè¿ĩ
    -0.09
    ules
    -0.08
    ç¾İçļĦ
    -0.08
    سب
    -0.08
    POSITIVE LOGITS
    ye
    0.10
    enticator
    0.10
    idan
    0.09
    ´
    0.09
    åŃº
    0.09
    лав
    0.09
    ((&
    0.09
    ingo
    0.08
    åĽ½éĻħæľºåľº
    0.08
    èľĢ
    0.08
    Activations Density 0.030%

    No Known Activations