© 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. 17537
    Prev
    Next
    INDEX
    Explanations

    what exactly

    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
    anke
    -0.11
    å·¨
    -0.09
    itto
    -0.09
    holm
    -0.08
    itures
    -0.08
    oulos
    -0.08
    ifton
    -0.08
    .ak
    -0.08
    äºĶåĪĨéĴŁ
    -0.08
    avana
    -0.08
    POSITIVE LOGITS
    éŨåīį
    0.10
    éĿ¢ä¸Ĭ
    0.09
    amber
    0.09
    cul
    0.09
     Unlimited
    0.08
    æݺ
    0.08
    åı°ä¸Ĭ
    0.08
    éĹ¨æ§Ľ
    0.08
    è¦ģç´§
    0.08
    loor
    0.08
    Activations Density 0.009%

    No Known Activations