© 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. 38649
    Prev
    Next
    INDEX
    Explanations

    does not exist

    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
    åĮħ
    -0.08
    нал
    -0.08
    åıĮéĩį
    -0.08
     Strong
    -0.08
    ä¸įåħĭ
    -0.08
    ä¸įæĢķ
    -0.08
    èį«
    -0.08
    ä¸įéĻIJ
    -0.08
    ä¸į容æĺĵ
    -0.08
    ä¸įä¸ĭ
    -0.08
    POSITIVE LOGITS
    å®ŀéĻħ
    0.14
    實éļĽ
    0.13
     ÑģобÑģÑĤвенно
    0.12
    çļĦå®ŀéĻħ
    0.12
    å®ŀéĻħä¸Ĭ
    0.12
     actual
    0.12
    actually
    0.10
    äºĭå®ŀä¸Ĭ
    0.10
    羣æŃ£çļĦ
    0.10
     actually
    0.10
    Activations Density 0.160%

    No Known Activations