© 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. 18728
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    ï¼Ĥ
    -0.09
    itical
    -0.09
    ’S
    -0.09
    们
    -0.08
    ä¸Ńæĸ°
    -0.08
     infl
    -0.08
    åĪĥ
    -0.08
    omas
    -0.08
    istic
    -0.08
    ãģĤãĤĭç¨ĭ度
    -0.08
    POSITIVE LOGITS
    s
    0.10
    åħ·ä½ĵçļĦ
    0.09
    åģļå¾Ĺ
    0.09
    åĽłä¸ºå®ĥ
    0.09
    pell
    0.09
    ä½Ĩå®ĥ
    0.09
    æĻĤåĢĻ
    0.09
    /is
    0.09
    æľ¬èº«çļĦ
    0.09
    cht
    0.08
    Activations Density 0.917%

    No Known Activations