© 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. 37537
    Prev
    Next
    INDEX
    Explanations

    Sung, ung, hung followed by names

    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
    istic
    -0.11
    侧ç»ĵæŀĦæĢ§
    -0.10
    åĽ¢éķ¿
    -0.10
    Ľ
    -0.10
    cloth
    -0.10
    åijĢ
    -0.10
    ingle
    -0.09
    pora
    -0.09
    å©¿
    -0.09
    ç¼ĥ
    -0.09
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.20
    uard
    0.10
    epend
    0.10
    retty
    0.09
    astic
    0.09
    ega
    0.09
    lico
    0.09
    itarian
    0.09
    adel
    0.09
    line
    0.08
    Activations Density 0.018%

    No Known Activations