© 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. 49180
    Prev
    Next
    INDEX
    Explanations

    behavioural and psychological concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    words describing coping behaviors, maladaptive responses, and symptoms related to trauma/mental health.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    å®īå±ħ
    -0.10
    让å®ĥ
    -0.10
    å®ŀåľ¨æĺ¯
    -0.10
    sus
    -0.09
    è¿ĻåĿĹ
    -0.09
    太大
    -0.09
    举起
    -0.09
    æ¯ĭ
    -0.08
    太è¿ĩ
    -0.08
    çĶļ
    -0.08
    POSITIVE LOGITS
    è´¬
    0.09
    æĪĸèĢħ
    0.08
    æĿ¥åĽŀ
    0.08
    以èī²
    0.08
    è·ĥ
    0.08
    ä¸į顾
    0.08
    线ä¸Ĭ线ä¸ĭ
    0.08
    eters
    0.08
    -hero
    0.08
    çľĭä¼¼
    0.08
    Activations Density 0.041%

    No Known Activations