© 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. 6623
    Prev
    Next
    INDEX
    Explanations

    step by step or numbered step

    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
    æľ¬ç½ijç«Ļ
    -0.10
    åĨµ
    -0.09
    éĤķ
    -0.09
    ä¸Ī
    -0.09
    乡
    -0.08
    åĸĥ
    -0.08
    èĥ¸åīį
    -0.08
    lox
    -0.08
    çī¹æ´¾åijĺ
    -0.08
    amber
    -0.08
    POSITIVE LOGITS
     step
    0.15
    æŃ¥éª¤
    0.15
    step
    0.13
     steps
    0.12
     Step
    0.12
     STEP
    0.11
    (step
    0.11
    STEP
    0.11
     stepped
    0.11
    Step
    0.10
    Activations Density 0.030%

    No Known Activations