© 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. 19748
    Prev
    Next
    INDEX
    Explanations

    members and representatives

    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
    踩
    -0.10
    åħħæĸ¥
    -0.10
    tml
    -0.10
    æĸ°å±ĢéĿ¢
    -0.09
    tees
    -0.09
    æĸ°è¥¿
    -0.09
    追éĢIJ
    -0.09
    ä½ĥ
    -0.09
    夹
    -0.09
    çĸ²
    -0.09
    POSITIVE LOGITS
    代表
    0.12
     representatives
    0.10
    æĿ¥èĩª
    0.10
    represent
    0.09
    ulty
    0.09
    å½ĵéĢī
    0.09
     representing
    0.08
     representa
    0.08
    çī½
    0.08
    çĥŃå¿ĥ
    0.08
    Activations Density 0.083%

    No Known Activations