© 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. 53485
    Prev
    Next
    INDEX
    Explanations

    community locations and activities

    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
    çī¹æ´¾
    -0.09
    èij±
    -0.09
    ä½ĵè´¨
    -0.09
    严å¯Ĩ
    -0.09
    建ç«ĭèµ·
    -0.09
    åĵģ
    -0.08
    asel
    -0.08
    éĵ²
    -0.08
    çŃ¹å¤ĩ
    -0.08
    士
    -0.08
    POSITIVE LOGITS
    ANO
    0.09
    夥
    0.09
    åĽłç´ł
    0.08
    vore
    0.08
    级以ä¸Ĭ
    0.08
     div
    0.08
    oler
    0.08
    åħ¸åŀĭ
    0.08
    hire
    0.08
     Hick
    0.07
    Activations Density 0.021%

    No Known Activations