© 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. 17367
    Prev
    Next
    INDEX
    Explanations

    stabbing, stab, jab

    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
    enne
    -0.10
     sÃłng
    -0.09
    vang
    -0.08
     dÃłng
    -0.08
    รà¸Ńà¸ĩ
    -0.08
    Eng
    -0.08
    ance
    -0.08
    éļľç¢į
    -0.08
    Seconds
    -0.08
    ench
    -0.08
    POSITIVE LOGITS
    èĽı
    0.09
    OrUpdate
    0.09
    itical
    0.09
    RELATED
    0.09
    ļ
    0.09
    æĿĤå¿Ĺ社
    0.09
    ä¿Ŀåį«
    0.09
    çİij
    0.09
     clue
    0.09
    gable
    0.09
    Activations Density 0.004%

    No Known Activations