© 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. 1109
    Prev
    Next
    INDEX
    Explanations

    way through

    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
    nts
    -0.09
    èĬĿ
    -0.09
    inqu
    -0.08
    è¿ľç¨ĭ
    -0.08
    éļı
    -0.08
    æĢģ
    -0.08
    rais
    -0.08
    大人
    -0.08
    ENCH
    -0.08
    (QL
    -0.08
    POSITIVE LOGITS
     way
    0.13
    ç©¿è¿ĩ
    0.12
    åĩºè·¯
    0.11
    è¿Ľåħ¥åĪ°
    0.11
    跻身
    0.10
    åīįè¿Ľ
    0.10
    è¿Ľåħ¥
    0.10
    æĬľãģij
    0.10
    éĢ²åħ¥
    0.10
    èµ°åĩºæĿ¥
    0.10
    Activations Density 0.033%

    No Known Activations