© 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. 6591
    Prev
    Next
    INDEX
    Explanations

    actions like stopping or persuading

    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
    TRS
    -0.10
    Rnd
    -0.09
    åľ¨è·¯ä¸Ĭ
    -0.09
    ÑĢай
    -0.09
    айд
    -0.08
    каÑĤ
    -0.08
    ilet
    -0.08
    æ±ĩ
    -0.08
    éĶī
    -0.08
    _SMALL
    -0.08
    POSITIVE LOGITS
    åĬĿ
    0.23
    åĪ¶æŃ¢
    0.17
    å¼ķ导
    0.13
    èѦåijĬ
    0.13
    æķĻ导
    0.13
    æıIJéĨĴ
    0.12
    åĵĦ
    0.12
    責
    0.12
    åĭ
    0.11
    éĺ»æŃ¢
    0.11
    Activations Density 0.090%

    No Known Activations