© 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. 27214
    Prev
    Next
    INDEX
    Explanations

    Chester 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
    举æŃ¢
    -0.10
    sWith
    -0.09
    ãģĤãģ£ãģ¦
    -0.09
    ä¾£
    -0.09
    arend
    -0.09
    LEN
    -0.09
    Õ·
    -0.09
    illy
    -0.09
    -0.09
    ç§ij室
    -0.09
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.10
    field
    0.09
    ained
    0.09
    æĸ°å¨ĺ
    0.08
    fall
    0.08
    ablish
    0.08
    æIJIJ
    0.08
    fold
    0.08
    ajan
    0.08
    éĻĭ
    0.08
    Activations Density 0.015%

    No Known Activations