© 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. 48270
    Prev
    Next
    INDEX
    Explanations

    average and percentage

    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
    å¹³åĿĩæ°´å¹³
    -0.11
    ä¸Ģéģį
    -0.10
    uka
    -0.09
    à¹Ĩ
    -0.09
     average
    -0.09
    ly
    -0.09
    å¹³åĿĩ
    -0.09
    çİĩè¾¾
    -0.09
     ime
    -0.09
    ä¸Ģ件äºĭ
    -0.09
    POSITIVE LOGITS
    -bs
    0.09
    ording
    0.09
    бол
    0.09
    elm
    0.08
    اج
    0.08
    _supported
    0.08
    è¿ĽæŃ¥
    0.08
    ç©°
    0.08
    antal
    0.08
     Hamp
    0.08
    Activations Density 0.146%

    No Known Activations