© 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. 32963
    Prev
    Next
    INDEX
    Explanations

    giving credit or props

    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
    ä¼Ĭ
    -0.08
     minded
    -0.08
    å¼ķåħ¥
    -0.08
    éĽĨä¸Ńåľ¨
    -0.08
    åĨ»ç»ĵ
    -0.08
    éĺı
    -0.08
    åľ¨å®¶
    -0.08
    æĥķ
    -0.08
    åİĦ
    -0.08
    velope
    -0.08
    POSITIVE LOGITS
    åĬŁåĬ³
    0.27
     credit
    0.23
    credit
    0.19
    Credit
    0.19
     Credit
    0.18
    _credit
    0.18
     credited
    0.17
    ä¿¡çĶ¨
    0.17
    .credit
    0.17
    åĬŁ
    0.15
    Activations Density 0.047%

    No Known Activations