© 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. 63469
    Prev
    Next
    INDEX
    Explanations

    and, far, &

    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
    å·´
    -0.08
    æµħ
    -0.08
    NodeType
    -0.08
    uber
    -0.08
    åĽ½å®ī
    -0.08
    atron
    -0.08
    _LL
    -0.08
    éĻĶ
    -0.08
     LL
    -0.08
    æľ
    -0.08
    POSITIVE LOGITS
    ç¡ķ
    0.10
    åł°
    0.09
    esco
    0.09
    ä¸ĢæŶ
    0.09
    ãĥķãĤ
    0.09
    æĤ´
    0.08
    æŃ¤äºº
    0.08
    ä¿¡æģ¯æĬĢæľ¯
    0.08
    NCY
    0.08
    PEG
    0.08
    Activations Density 0.111%

    No Known Activations