© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8149
    Prev
    Next
    INDEX
    Explanations

    impairment or impaired function

    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
    æĹ¶è£ħ
    -0.10
    æ»ļæ»ļ
    -0.10
    ä¼ģä¸ļæıIJä¾Ľ
    -0.09
    æ·±åħ¥å¼Ģå±ķ
    -0.09
    /current
    -0.09
    çĽij管éĥ¨éŨ
    -0.09
    è§ģéĿ¢
    -0.09
    eller
    -0.09
    ä¸Ģ份
    -0.09
    POSITIVE LOGITS
    ments
    0.13
    ment
    0.11
    ç¤Ļ
    0.09
    ç͍åĵģ
    0.09
    /dis
    0.09
    aje
    0.08
    _subtype
    0.08
    mented
    0.08
    uos
    0.08
    æ¤Ĵ
    0.08
    Activations Density 0.086%

    No Known Activations