© 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. 2179
    Prev
    Next
    INDEX
    Explanations

    ISO 9001 certification

    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
    追赶
    -0.09
    çIJĨå·¥
    -0.09
    çķ¥æľī
    -0.09
    ialis
    -0.09
    æĮ½åĽŀ
    -0.09
    tip
    -0.09
    å®ķ
    -0.08
    DMIN
    -0.08
    æ½Ń
    -0.08
    çŃĸ
    -0.08
    POSITIVE LOGITS
    è¡ĮåĪĹ
    0.10
    ichi
    0.09
    gle
    0.09
    åĬ²
    0.08
    èĥ¼
    0.08
    uffers
    0.08
     Pit
    0.08
    åIJĪä¸Ģ
    0.08
    ãĥķãĥ«
    0.08
    èµ°åĪ°
    0.08
    Activations Density 0.054%

    No Known Activations