© 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. 57067
    Prev
    Next
    INDEX
    Explanations

    URL file extensions

    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
    pole
    -0.10
    orage
    -0.09
    çİ«
    -0.09
    æĤĴ
    -0.09
    uya
    -0.09
    èľĪ
    -0.09
    íĭĢ
    -0.09
    ixa
    -0.08
    èµ³
    -0.08
    åħ¬åı¸ç«łç¨ĭ
    -0.08
    POSITIVE LOGITS
    æĺİæĺİ
    0.09
    etre
    0.08
    éĢĨè¡Į
    0.08
    ä¹IJåĽŃ
    0.08
    intr
    0.08
    æ®Ĭ
    0.08
    Cas
    0.07
    meric
    0.07
    ure
    0.07
    åħ´èµ·
    0.07
    Activations Density 0.139%

    No Known Activations