© 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. 58646
    Prev
    Next
    INDEX
    Explanations

    words describing shape

    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
    ä¹ĭ声
    -0.09
    able
    -0.09
    eneg
    -0.08
    çĶŁæ´»ä¸Ń
    -0.08
    æĢ§çĸ¾çĹħ
    -0.08
    [](
    -0.08
    åħĸ
    -0.08
    ãĥ©
    -0.08
    ä¸Ģ个æĸ°çļĦ
    -0.08
    hound
    -0.08
    POSITIVE LOGITS
    å¡Ĭ
    0.10
    æ¶Ľ
    0.09
    岿
    0.09
    èĢĥå¯Ł
    0.09
    isle
    0.08
    ocache
    0.08
    è¯İ
    0.08
    sWith
    0.08
    md
    0.08
     defaultCenter
    0.08
    Activations Density 0.036%

    No Known Activations