© 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. 21687
    Prev
    Next
    INDEX
    Explanations

    contents of

    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
     scor
    -0.09
    ONES
    -0.09
     rem
    -0.09
    дж
    -0.09
    ÑĤоÑĢ
    -0.08
    تÙĩ
    -0.08
    éģ
    -0.08
    burst
    -0.08
    onomy
    -0.08
    -minded
    -0.08
    POSITIVE LOGITS
    åı¯æĥ³
    0.11
    åĬĽäºī
    0.10
    rate
    0.10
    ramework
    0.09
    ugg
    0.09
    æĶ¸
    0.09
    ãģĹãģ¾
    0.08
    ãģĹãģ¾ãģĨ
    0.08
    TimeInterval
    0.08
    cheid
    0.08
    Activations Density 0.014%

    No Known Activations