© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7021
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    EMBER
    -0.11
    æľī人
    -0.09
    æµģè¡ĮçļĦ
    -0.09
    æį¶
    -0.09
    åĩºåĩ»
    -0.09
    æľĽåİ»
    -0.08
    osos
    -0.08
    ETO
    -0.08
    ary
    -0.08
    大éŨ
    -0.08
    POSITIVE LOGITS
    为代表çļĦ
    0.10
     pig
    0.10
    scores
    0.09
    -hole
    0.09
    /her
    0.09
    åı£ä¸Ń
    0.09
     sag
    0.08
    âľī
    0.08
    pig
    0.08
    ç»°
    0.08
    Activations Density 0.599%

    No Known Activations