© 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. 34557
    Prev
    Next
    INDEX
    Explanations

    motherboard parts and electronics

    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
    éĽĨè£ħ
    -0.10
    æİ¥åĬĽ
    -0.08
    otte
    -0.08
    èĩ¨
    -0.08
    yne
    -0.08
    绳
    -0.08
    Materials
    -0.08
    è¿ĺä¸įå¦Ĥ
    -0.08
    èĺ§
    -0.08
     neutral
    -0.08
    POSITIVE LOGITS
    é©·
    0.10
    ixon
    0.10
    éĩįå·¥
    0.10
    é³Ŀ
    0.09
    -spe
    0.09
    _imm
    0.09
    ecer
    0.08
    ÙħÙĬÙĨ
    0.08
     Flush
    0.08
    å§ĭ
    0.08
    Activations Density 0.023%

    No Known Activations