© 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. 62919
    Prev
    Next
    INDEX
    Explanations

    engine noises and issues

    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
    æ°¸ä¸į
    -0.10
    æİĺ
    -0.09
    -lat
    -0.09
    _latency
    -0.08
    ç»ĻæĪij们
    -0.08
    ä¸įçķĻ
    -0.08
    WXYZ
    -0.08
    ä¸Ģèīĺ
    -0.08
    让èĩªå·±
    -0.08
    åIJİåı°
    -0.08
    POSITIVE LOGITS
    表çİ°
    0.09
    xcb
    0.09
    ESCO
    0.09
    æ®·
    0.09
    _dy
    0.08
    engage
    0.08
    å£°éŁ³
    0.08
    èĩ³ä¸Ĭ
    0.08
    onica
    0.08
    è¿ľæĻ¯
    0.08
    Activations Density 0.085%

    No Known Activations