© 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. 22667
    Prev
    Next
    INDEX
    Explanations

    weakness and strength

    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
    ä¸įçŁ¥ä¸į
    -0.08
    arios
    -0.08
    Ñģ
    -0.08
    çļĦæĪĺçķ¥
    -0.08
    isper
    -0.08
    å¾Īå¤ļçݩ家
    -0.08
    误ä¼ļ
    -0.08
    æĻ®åıĬ
    -0.08
    isd
    -0.08
    coat
    -0.08
    POSITIVE LOGITS
    强åĬ²
    0.10
    å¸ĤåľºéľĢæ±Ĥ
    0.10
    å¸Ĥåľºä»·æł¼
    0.10
    æīĢå¾Ĺ
    0.09
    /conf
    0.09
    Spl
    0.09
    vil
    0.09
    ACTER
    0.09
    ÑĢÑĥк
    0.08
    tero
    0.08
    Activations Density 0.021%

    No Known Activations