© 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. 2751
    Prev
    Next
    INDEX
    Explanations

    thank you for the reply and suggestion

    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
    ç»°
    -0.09
    æĽĻåħī
    -0.09
    /ajax
    -0.09
    mie
    -0.09
    æł¼
    -0.09
    irl
    -0.09
    FromArray
    -0.09
    ons
    -0.08
    çļĦ表çİ°
    -0.08
    _FLASH
    -0.08
    POSITIVE LOGITS
     Excell
    0.10
    å®Ŀè´µçļĦ
    0.09
    å¤ļæķ°
    0.09
    äºĨæĪijçļĦ
    0.09
    /questions
    0.09
     indeed
    0.09
    åIJİèĢħ
    0.09
     cand
    0.09
    abet
    0.09
    帮æĪij
    0.09
    Activations Density 0.041%

    No Known Activations