© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51342
    Prev
    Next
    INDEX
    Explanations

    apprenticeships and indentures

    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
    ĺ
    -0.13
    berman
    -0.09
     eleg
    -0.09
    å±ħ
    -0.09
    à¹Ĥà¸Ħร
    -0.09
    åħ³åĪĩ
    -0.09
    ÑĤоÑĢ
    -0.09
    æĭ¥
    -0.08
    CED
    -0.08
    æµ·å¤ĸ
    -0.08
    POSITIVE LOGITS
    دÙĬØ©
    0.11
    缨
    0.11
    hips
    0.10
    ettle
    0.10
    uib
    0.10
    åħ¨æĹ¥
    0.09
    ÑģÑģ
    0.09
    arily
    0.09
    ees
    0.09
    ä¸ĢéĿ¢
    0.09
    Activations Density 0.004%

    No Known Activations