© 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. 4407
    Prev
    Next
    INDEX
    Explanations

    either: or

    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
    åħ¶å®ŀå°±æĺ¯
    -0.11
    åıªä¸įè¿ĩæĺ¯
    -0.11
    åħ¶å®ŀæĺ¯
    -0.11
    åħ¶å®ŀ
    -0.10
    丼æŀĹ
    -0.10
    åij¸
    -0.10
    æį®è¯´
    -0.10
    å¦Ĥæŀľä¸įæĺ¯
    -0.10
    çĽ¸ä¼ł
    -0.09
    essen
    -0.09
    POSITIVE LOGITS
    /all
    0.11
    wel
    0.11
    ç¿ķ
    0.10
    主è§Ĥ
    0.10
    æĺ¯åľ¨
    0.09
    亢
    0.09
    -than
    0.09
    /e
    0.08
    enco
    0.08
    ä»Ģä¹ĪåİŁåĽł
    0.08
    Activations Density 0.034%

    No Known Activations