© 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. 49069
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    çķ²
    -0.10
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.10
    çĸĥ
    -0.09
    éĨī
    -0.09
    à¸ģว
    -0.09
    å»Ł
    -0.09
    OrCreate
    -0.09
    epad
    -0.09
    å²ģæŶ
    -0.09
    æĸ¡
    -0.08
    POSITIVE LOGITS
     bug
    0.08
    åĩī
    0.08
    è¯Ī
    0.08
    atte
    0.08
    _hal
    0.08
    çļĦä¸Ģ大
    0.08
    éĢ
    0.08
    æ´ĭèij±
    0.08
    _tw
    0.08
    _compat
    0.07
    Activations Density 0.089%

    No Known Activations