© 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. 6446
    Prev
    Next
    INDEX
    Explanations

    touching on

    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
    strate
    -0.10
    ä½İ头
    -0.09
    emo
    -0.09
    è§Ĩè§Ĵ
    -0.09
    checker
    -0.09
    eur
    -0.08
    æĬ¬å¤´
    -0.08
    aris
    -0.08
    inged
    -0.08
    èĵį
    -0.08
    POSITIVE LOGITS
    ABLE
    0.11
    UpInside
    0.11
    OrCreate
    0.11
    ãĥ³ãĤ°
    0.10
    able
    0.10
    Began
    0.10
    ably
    0.10
    heet
    0.10
    backs
    0.10
    -pad
    0.09
    Activations Density 0.027%

    No Known Activations