© 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. 33602
    Prev
    Next
    INDEX
    Explanations

    utica

    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
    常å§Ķä¼ļ
    -0.10
    åIJĪãĤıãģĽ
    -0.10
    еÑĢж
    -0.09
    ëģĶ
    -0.09
    .hr
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    å°¤åħ¶æĺ¯
    -0.08
    ãĥ¼ãĤº
    -0.08
    .gms
    -0.08
    æł·çļĦ
    -0.08
    POSITIVE LOGITS
    ties
    0.15
    ted
    0.14
    ters
    0.13
    most
    0.13
    ting
    0.12
    Ŀå§ĭ
    0.10
    TING
    0.10
    tes
    0.09
    ites
    0.09
    TER
    0.09
    Activations Density 0.048%

    No Known Activations