© 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. 53487
    Prev
    Next
    INDEX
    Explanations

    as [noun] as [noun]

    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
     Crusher
    -0.10
    Ñĥв
    -0.09
    æļĹ
    -0.09
    æĹłå£°
    -0.09
    LETE
    -0.08
     Slate
    -0.08
    ermann
    -0.08
    åĩºåħ¥å¢ĥ
    -0.08
    尤为
    -0.08
    .NewLine
    -0.08
    POSITIVE LOGITS
    èĥ½æĬĬ
    0.10
    æĪijå½ĵæŶ
    0.09
    urai
    0.09
    æīĢæıIJä¾ĽçļĦ
    0.08
    æ²¾
    0.08
    æ·ħ
    0.08
    (dec
    0.08
    çĻ»
    0.08
    åı¯éĿłçļĦ
    0.08
    æīĢæıIJä¾Ľ
    0.08
    Activations Density 0.034%

    No Known Activations