© 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. 22594
    Prev
    Next
    INDEX
    Explanations

    without express or indicated

    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
    亨
    -0.10
    顺
    -0.10
    /browse
    -0.10
    éłĨ
    -0.09
    pite
    -0.09
    å·±
    -0.08
    çķļ
    -0.08
    ULO
    -0.08
    precision
    -0.08
    顺åĬ¿
    -0.08
    POSITIVE LOGITS
    raud
    0.09
    çŁ³å®¶
    0.08
     emb
    0.08
    жд
    0.08
    fila
    0.08
    رة
    0.08
    好ä¸į好
    0.08
    lags
    0.08
    1
    0.08
    weise
    0.08
    Activations Density 0.068%

    No Known Activations