© 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. 22692
    Prev
    Next
    INDEX
    Explanations

    wizard

    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
    TING
    -0.11
    说æĺ¯
    -0.09
    clipse
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    ening
    -0.09
    voke
    -0.08
    cker
    -0.08
    èŁł
    -0.08
    满äºĨ
    -0.08
    ings
    -0.08
    POSITIVE LOGITS
    ry
    0.16
    们éĥ½
    0.11
    ../../../
    0.10
    们çļĦ
    0.10
    olph
    0.10
    为æ°ij
    0.10
    _Base
    0.10
    las
    0.09
    们
    0.09
    ¶
    0.09
    Activations Density 0.006%

    No Known Activations