© 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. 2741
    Prev
    Next
    INDEX
    Explanations

    energy conversion

    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
    bler
    -0.09
     retro
    -0.09
     pron
    -0.09
    çĶ¸
    -0.09
     ÑģоÑģÑĤав
    -0.08
    çĽĺ
    -0.08
    è®®
    -0.08
    åħ±åIJĮ
    -0.08
     plug
    -0.08
    æĹĨ
    -0.08
    POSITIVE LOGITS
    èĥ½éĩı
    0.17
    çļĦèĥ½éĩı
    0.15
     energy
    0.14
     ÑįнеÑĢги
    0.14
    energy
    0.13
    ãĤ¨ãĥįãĥ«ãĤ®ãĥ¼
    0.13
     Energy
    0.12
    .energy
    0.12
    Energy
    0.11
    _energy
    0.11
    Activations Density 0.144%

    No Known Activations