© 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. 56266
    Prev
    Next
    INDEX
    Explanations

    carved

    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
    /devices
    -0.09
    åĢĻ
    -0.08
    enny
    -0.08
    oral
    -0.08
    -paid
    -0.08
     shield
    -0.08
    ric
    -0.08
     пÑĥÑĤ
    -0.08
    âĶĹ
    -0.08
    /autoload
    -0.08
    POSITIVE LOGITS
    icular
    0.10
    åĩºæĿ¥çļĦ
    0.10
    ä¸įåĩºæĿ¥
    0.10
    å¾Ĺå¾Ī
    0.09
    åīĬ
    0.09
    å¶Ļ
    0.09
    åµĺ
    0.09
    OrUpdate
    0.09
    èĢĮæĪIJ
    0.09
     пÑĢоиÑģ
    0.09
    Activations Density 0.010%

    No Known Activations