© 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. 20148
    Prev
    Next
    INDEX
    Explanations

    A followed by publication type

    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
    çĭł
    -0.08
     ìĭ
    -0.08
    çĥ½
    -0.08
    åĽ´
    -0.08
    ALTH
    -0.08
    0
    -0.08
    诸å¦Ĥ
    -0.08
    .dll
    -0.07
    3
    -0.07
    4
    -0.07
    POSITIVE LOGITS
    åİ»çľĭçľĭ
    0.11
     ÑģÑĤоим
    0.10
    ÑĦÑĤ
    0.10
    нÑĮ
    0.10
    ä¸įåłª
    0.10
    èİ«æĸ¯
    0.10
    è¹ij
    0.09
    人å±ħ
    0.09
    ä¸įèĩ³äºİ
    0.09
    ä¿İ
    0.09
    Activations Density 0.078%

    No Known Activations