© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37575
    Prev
    Next
    INDEX
    Explanations

    following "move"

    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
    ardy
    -0.09
    _interrupt
    -0.09
    è¿Ļç±»
    -0.09
    itarian
    -0.08
    æĺİçĻ½äºĨ
    -0.08
    åĿĽ
    -0.08
     плаÑĤ
    -0.08
    åĢļ
    -0.08
    vac
    -0.08
    ä¸Ģéĥ¨
    -0.08
    POSITIVE LOGITS
    æŃ¤ä¸¾
    0.13
    举æݪ
    0.12
    举åĬ¨
    0.10
    å®īæİĴ
    0.10
    åģļæ³ķ
    0.10
    è¿Ļä¹Īåģļ
    0.09
    ëĶ°
    0.09
    使æĪij
    0.09
    åħ¬æĬ¥
    0.09
    ä¸Ī夫
    0.09
    Activations Density 0.071%

    No Known Activations