© 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. 19163
    Prev
    Next
    INDEX
    Explanations

    prior art

    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
    ëģĶ
    -0.11
    APE
    -0.10
    sam
    -0.10
    endo
    -0.10
    ãģıãĤĭ
    -0.10
    åºĶæĶ¶
    -0.09
    å±ĭåŃIJ
    -0.09
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.09
    uar
    -0.09
    ãģ®ãģĮ
    -0.09
    POSITIVE LOGITS
    itized
    0.14
    itize
    0.14
    ities
    0.13
    mente
    0.11
    duct
    0.11
    centage
    0.11
    lane
    0.10
    emente
    0.10
    è¾Ī
    0.10
    иÑĤеÑĤ
    0.09
    Activations Density 0.029%

    No Known Activations