© 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. 53790
    Prev
    Next
    INDEX
    Explanations

    "I" followed by a conjunction or verb

    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
    agt
    -0.10
    _VC
    -0.08
    ril
    -0.08
     GPLv
    -0.08
    ãĤ§
    -0.08
    iller
    -0.08
    èĢķ
    -0.08
     Stark
    -0.07
    æ«
    -0.07
    .collections
    -0.07
    POSITIVE LOGITS
    æĢİä¹ĪåĽŀäºĭ
    0.14
    åİŁåĽłæĺ¯
    0.12
    ä»Ģä¹ĪåİŁåĽł
    0.11
    åı¯èĥ½æĺ¯
    0.11
    说æĺ¯
    0.10
    éĹ®é¢ĺæĺ¯
    0.10
    请éĹ®
    0.10
    ä¸įæŃ¢
    0.09
    cies
    0.09
    æľī人说
    0.09
    Activations Density 0.522%

    No Known Activations