© 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. 33464
    Prev
    Next
    INDEX
    Explanations

    all- followed by word

    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
    _allowed
    -0.09
    éĻIJ度
    -0.09
    ÑĪка
    -0.09
    èĥ½å¾ĹåĪ°
    -0.08
    æĿ¡ä¾ĭ
    -0.08
    æĹłèģĬ
    -0.08
    yla
    -0.08
    å¨ħ
    -0.08
    çļ¿
    -0.08
    ë§IJ
    -0.08
    POSITIVE LOGITS
    ot
    0.11
    nder
    0.10
    uded
    0.09
    ror
    0.09
    ness
    0.09
    er
    0.09
    enger
    0.09
    am
    0.08
    ong
    0.08
    oded
    0.08
    Activations Density 0.014%

    No Known Activations