© 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. 51783
    Prev
    Next
    INDEX
    Explanations

    Midlands location 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
    åı£è¢ĭ
    -0.13
    ocket
    -0.10
    ç¬ijèĦ¸
    -0.09
    ablo
    -0.09
    åīįéĶĭ
    -0.09
    umes
    -0.09
    涧
    -0.09
    loor
    -0.08
    èĻı
    -0.08
    æģ¯
    -0.08
    POSITIVE LOGITS
    ÐŀÐł
    0.09
    izers
    0.09
    amar
    0.08
    rarian
    0.08
    çŃł
    0.08
    alice
    0.08
    odon
    0.08
    gst
    0.08
    _SAMPLES
    0.08
    ieg
    0.08
    Activations Density 0.001%

    No Known Activations