© 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. 17459
    Prev
    Next
    INDEX
    Explanations

    dividing or distributing among

    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
    çĽ²
    -0.10
     Spir
    -0.09
    åįķ纯çļĦ
    -0.09
    enames
    -0.08
    flu
    -0.08
    è´´
    -0.08
    gems
    -0.08
    ä½ľå®¶
    -0.08
    沦
    -0.08
    ä¸ĢæŶ
    -0.08
    POSITIVE LOGITS
    åĪĨéħį
    0.12
    两åıª
    0.11
    åĪĨæĪIJ
    0.11
    åĪĨå¸ĥåľ¨
    0.10
     split
    0.10
    èµĤ
    0.10
    åİ»äºĨ
    0.10
     distribute
    0.09
    åĿĩè¡¡
    0.09
    .Split
    0.09
    Activations Density 0.075%

    No Known Activations