© 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. 1409
    Prev
    Next
    INDEX
    Explanations

    literary agency

    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
    sha
    -0.10
    æĮĩçĿĢ
    -0.10
     Dexter
    -0.09
    åľ°åĿª
    -0.09
    å¸ħæ°Ķ
    -0.09
    å±Ī
    -0.09
    æ³¼
    -0.09
     flexGrow
    -0.09
    羣åģĩ
    -0.09
    Fil
    -0.09
    POSITIVE LOGITS
    ÐłÐIJ
    0.09
    ç¿ĺ
    0.09
    罨
    0.09
    åī§æľ¬
    0.09
    第ä¸ĢæĿ¡
    0.08
     rejection
    0.08
    ç®ĢåİĨ
    0.08
    ải
    0.08
     submitting
    0.08
    Pitch
    0.08
    Activations Density 0.093%

    No Known Activations