© 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. 4879
    Prev
    Next
    INDEX
    Explanations

    scrib, scrible, Scripps, Scribe

    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
    ioned
    -0.11
    ector
    -0.11
    aroo
    -0.09
    é»ĺå¥ij
    -0.09
    ted
    -0.09
    sgi
    -0.08
    аÑĨион
    -0.08
    Ñĩив
    -0.08
    ë°Ģ
    -0.08
    ancing
    -0.08
    POSITIVE LOGITS
    âľį
    0.11
    æĪŁ
    0.10
    ums
    0.10
    ä¿¡ç®±
    0.09
    dır
    0.09
    帽
    0.09
    pad
    0.09
    åĩłåı¥
    0.09
    ä¿ij
    0.09
    OrUpdate
    0.09
    Activations Density 0.021%

    No Known Activations