© 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. 18432
    Prev
    Next
    INDEX
    Explanations

    leftover food or things

    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
    æıĸ
    -0.13
    ural
    -0.10
    inned
    -0.09
    æ±ĤåĬ©
    -0.09
    ä»¥äººä¸ºæľ¬
    -0.09
    ÙĪار
    -0.09
    çĹĴ
    -0.08
    /or
    -0.08
    aban
    -0.08
    raid
    -0.08
    POSITIVE LOGITS
    swith
    0.11
    å¿Ŀ
    0.10
    åĬłçĽĸ
    0.09
     tame
    0.09
    sWith
    0.08
    èĤĥ
    0.08
    èĮĢ
    0.08
    amil
    0.08
    åĢij
    0.08
     metab
    0.08
    Activations Density 0.003%

    No Known Activations