© 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. 26870
    Prev
    Next
    INDEX
    Explanations

    brush borders

    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
     Hav
    -0.10
    Orig
    -0.09
    çīĻ
    -0.09
    çłĶ究ä¸Ńå¿ĥ
    -0.09
    ULE
    -0.08
    çĤ¹éĴŁ
    -0.08
    orig
    -0.08
    uss
    -0.08
    idon
    -0.08
    edu
    -0.08
    POSITIVE LOGITS
    andi
    0.10
    æļĤç¼ĵ
    0.10
    sigmoid
    0.09
    çĵ´
    0.09
    gies
    0.09
    åħ¨åĽ½äººæ°ij
    0.09
    饱
    0.08
    fiber
    0.08
    å®Ľ
    0.08
    à¹Ĥà¸ģ
    0.08
    Activations Density 0.014%

    No Known Activations