© 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. 33349
    Prev
    Next
    INDEX
    Explanations

    retreat and devotion

    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
    vana
    -0.09
    ities
    -0.09
    è°µ
    -0.08
     impr
    -0.08
    oko
    -0.08
    _crc
    -0.08
    dl
    -0.08
    ä¸ĬåѦ
    -0.08
    iane
    -0.08
    è¾ī
    -0.08
    POSITIVE LOGITS
    ä¹ħä¹ħ
    0.09
    åį³å°ĨåĪ°æĿ¥
    0.09
    ç«Ł
    0.08
    ersen
    0.08
    èĪ¬
    0.08
    geries
    0.08
    ESH
    0.08
    æıŃ示
    0.08
    stood
    0.08
    lage
    0.08
    Activations Density 0.002%

    No Known Activations