© 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. 33976
    Prev
    Next
    INDEX
    Explanations

    Wade

    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
    sWith
    -0.13
    ï¸
    -0.09
    ations
    -0.09
    è¯Ī
    -0.09
    phans
    -0.09
    ย
    -0.09
    ãĤį
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    ìĬ¬
    -0.09
    ivity
    -0.08
    POSITIVE LOGITS
    овÑĭй
    0.10
    itional
    0.09
    å¸ĪåĤħ
    0.09
    zilla
    0.09
    itte
    0.09
    nable
    0.09
    åħµåĽ¢
    0.09
    kick
    0.09
    ì§ľ
    0.09
    åĽŀäºĭ
    0.09
    Activations Density 0.003%

    No Known Activations