© 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. 37351
    Prev
    Next
    INDEX
    Explanations

    goals scored

    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
    åĪĽ
    -0.09
    apy
    -0.09
    æݧ
    -0.09
    æį§
    -0.08
    èĻİ
    -0.08
    æŁ¥çľĭ详æĥħ
    -0.08
    糧
    -0.08
    ocos
    -0.08
    odel
    -0.08
    apos
    -0.08
    POSITIVE LOGITS
    è¿ĽçIJĥ
    0.12
    ä¸įå¿ĺ
    0.11
    âļ½
    0.10
    Ãłnh
    0.10
    cid
    0.09
    äºĭåIJİ
    0.09
     goals
    0.09
    çł´
    0.09
    è¯ŀçĶŁ
    0.09
    âĦħ
    0.09
    Activations Density 0.074%

    No Known Activations