© 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. 30759
    Prev
    Next
    INDEX
    Explanations

    equipment and devices

    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
    è°¢
    -0.10
    è¬Ŀ
    -0.10
    缨
    -0.09
    LAY
    -0.08
    度
    -0.08
    adol
    -0.08
    agini
    -0.08
    AxisSize
    -0.08
    >--
    -0.08
    (errno
    -0.08
    POSITIVE LOGITS
    ä¸Ģ次æĢ§
    0.09
    å¤ļä¹Ī
    0.09
    è§Ħ模
    0.08
    ety
    0.08
    å·¥ä½ľå®¤
    0.08
    æį£
    0.08
    isy
    0.08
    ç¢Ľ
    0.08
    æįĭ
    0.08
    为èĩªå·±
    0.08
    Activations Density 0.101%

    No Known Activations