© 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. 61006
    Prev
    Next
    INDEX
    Explanations

    volume and capacity units

    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
    人å¿ĥ
    -0.10
    borough
    -0.10
    æĸŃè£Ĥ
    -0.08
     باÙĦÙĨ
    -0.08
    rad
    -0.08
    æĪĴ
    -0.08
     Boards
    -0.08
    è´´
    -0.08
    æĬµ
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
    容éĩı
    0.17
     volumes
    0.14
    缼
    0.13
     capacity
    0.13
    ä½ĵ积
    0.13
     volume
    0.13
     capacities
    0.12
    çĵ¶åŃIJ
    0.12
    çĵ¶
    0.12
    æ¸ħæ°´
    0.12
    Activations Density 0.116%

    No Known Activations