© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52595
    Prev
    Next
    INDEX
    Explanations

    indian names

    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
    abic
    -0.09
    habit
    -0.09
     fle
    -0.08
    .ReadAll
    -0.08
    ++++++++
    -0.08
    åĭĴ
    -0.08
     backing
    -0.08
    ÑĤеÑĢ
    -0.08
     Kou
    -0.08
    çľĩ
    -0.08
    POSITIVE LOGITS
    idal
    0.09
    ered
    0.09
    chet
    0.09
    çĿ¬
    0.08
    gy
    0.08
    cip
    0.08
    è¿ĺç®Ĺ
    0.08
     Gy
    0.08
    ä¼łæĴŃ
    0.08
    è¾°
    0.08
    Activations Density 0.050%

    No Known Activations