© 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. 27936
    Prev
    Next
    INDEX
    Explanations

    fish and fishing terms

    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
    ÑĢаÑģÑĤ
    -0.10
    ä¸Ģæīĭ
    -0.10
    为æ°ij
    -0.09
    éĵŁ
    -0.09
    çĪ±ä½ł
    -0.08
    åľ°æĸ¹
    -0.08
    åı¯æĢľ
    -0.08
    æĪijå¿ĥéĩĮ
    -0.08
    èĬľ
    -0.08
    è¿ĪåIJij
    -0.08
    POSITIVE LOGITS
    unsch
    0.09
    .targets
    0.09
    onis
    0.09
    æĭIJ
    0.09
    URNS
    0.09
    [".
    0.09
    igion
    0.09
    leans
    0.09
    glass
    0.08
    InitStruct
    0.08
    Activations Density 0.013%

    No Known Activations