© 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. 61814
    Prev
    Next
    INDEX
    Explanations

    Siberia, New Hampshire, bacteria

    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
    é¢IJ
    -0.10
    èĥİ
    -0.09
    vic
    -0.09
     Vic
    -0.09
    æĶ¸
    -0.08
    æIJº
    -0.08
    æ·¬
    -0.08
    ULK
    -0.08
    DCF
    -0.08
    禧
    -0.08
    POSITIVE LOGITS
    undra
    0.10
    豪
    0.09
    ä¸įæŃ»
    0.09
    èįīåİŁ
    0.08
    gon
    0.08
    奢ä¾Ī
    0.08
    渴
    0.08
    éķIJ
    0.08
    奢
    0.08
    .expression
    0.08
    Activations Density 0.123%

    No Known Activations