© 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. 39992
    Prev
    Next
    INDEX
    Explanations

    technical jobs and roles

    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
    raud
    -0.09
    楹
    -0.09
    åĪĨè¡Į
    -0.09
    åĪĨå¸ĥåľ¨
    -0.09
    inding
    -0.09
    赤
    -0.09
    缮çļĦåľ¨äºİ
    -0.08
    åħij
    -0.08
    ently
    -0.08
    弧
    -0.08
    POSITIVE LOGITS
    æĶ¿åĬ¡æľįåĬ¡
    0.10
    çļĦåŁºæľ¬
    0.09
    åĩĨ
    0.09
    pite
    0.09
    åľ¨å®¶éĩĮ
    0.09
    éĺIJ
    0.08
    åĵ¨
    0.08
    /plain
    0.08
    颤æĬĸ
    0.08
    -runtime
    0.08
    Activations Density 0.129%

    No Known Activations