© 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. 33608
    Prev
    Next
    INDEX
    Explanations

    Monster Hunter

    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
    åĪ¶åº¦æĶ¹éĿ©
    -0.10
    crest
    -0.10
    ump
    -0.10
    è¿Ļç§įæĸ¹å¼ı
    -0.09
    rite
    -0.09
    oop
    -0.09
    工夫
    -0.09
    istry
    -0.09
    ONS
    -0.09
    ons
    -0.09
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.10
    ions
    0.09
    bilt
    0.09
    trak
    0.09
    appen
    0.09
    ä¹Łå¸ĮæľĽ
    0.09
    pig
    0.09
    olini
    0.08
    ously
    0.08
    æĿ¥çĶµ
    0.08
    Activations Density 0.013%

    No Known Activations