© 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. 38089
    Prev
    Next
    INDEX
    Explanations

    nutritional needs or supporting position

    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
    анÑģ
    -0.11
    ç¾Ĭ
    -0.10
    èĤ¤
    -0.08
    é¤IJæ¡Į
    -0.08
    inan
    -0.08
    igar
    -0.08
    çķª
    -0.08
    è¿IJè¡Į
    -0.07
    æĻĴ
    -0.07
    dom
    -0.07
    POSITIVE LOGITS
    å®Įæķ´æĢ§
    0.10
     Diss
    0.09
    åĪ©çĽĬ
    0.09
    çIJ¨
    0.09
    æĬ¤
    0.09
    ugg
    0.09
    è¶Ĭ好
    0.09
    大èĤ¡ä¸ľ
    0.09
    åŃļ
    0.09
    ibble
    0.09
    Activations Density 0.062%

    No Known Activations