© 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. 4455
    Prev
    Next
    INDEX
    Explanations

    reimbursement

    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
    ateur
    -0.11
    é¼IJ
    -0.10
    éĻ¤å¤ķ
    -0.10
    辫
    -0.09
     há»ĵi
    -0.09
    alker
    -0.09
    oting
    -0.09
    ä¸Ľä¹¦
    -0.08
    bum
    -0.08
    ereal
    -0.08
    POSITIVE LOGITS
    able
    0.12
    ably
    0.11
    edly
    0.10
    åŃĿ
    0.09
    å¾Ĺèµ·
    0.09
    canonical
    0.09
    alte
    0.09
    lix
    0.09
    ingly
    0.09
    é¼ĭ
    0.08
    Activations Density 0.003%

    No Known Activations