© 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. 17157
    Prev
    Next
    INDEX
    Explanations

    mud

    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
    nels
    -0.10
    çŀ©
    -0.10
    TRS
    -0.10
    ç¾İ好
    -0.09
    oire
    -0.09
    nel
    -0.09
    åĩĿèģļ
    -0.09
    ality
    -0.09
    é£İåIJ¹
    -0.09
    à¸ĵ
    -0.08
    POSITIVE LOGITS
    gin
    0.10
    é³ħ
    0.10
    0.10
    din
    0.09
    æ³ŀ
    0.09
    gy
    0.09
    bound
    0.09
    gie
    0.09
    ged
    0.09
    ialect
    0.09
    Activations Density 0.009%

    No Known Activations