© 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. 1666
    Prev
    Next
    INDEX
    Explanations

    utf followed by dash

    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
     tran
    -0.10
    éĻĽ
    -0.10
    cir
    -0.09
    ä¸įè§ģ
    -0.09
    åıĺåİĭ
    -0.09
    娲
    -0.09
    ôt
    -0.08
    /or
    -0.08
    ä¸įæŃ»
    -0.08
    antino
    -0.08
    POSITIVE LOGITS
    éĢł
    0.11
    æ¼Ĥæµģ
    0.09
    å¯ħ
    0.09
    åĨ·æ°´
    0.09
     Sle
    0.09
    è¯Ĩ
    0.09
    ä¿®
    0.08
    overs
    0.08
    æī«
    0.08
    åľŃ
    0.08
    Activations Density 3.432%

    No Known Activations