© 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. 11394
    Prev
    Next
    INDEX
    Explanations

    robbery and heist terminology

    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
    è¾Ł
    -0.10
    ç¨Ĺ
    -0.10
    æĹłæķĪ
    -0.10
    马åħĭ
    -0.09
    庸
    -0.09
    بات
    -0.09
     Hearth
    -0.09
    馨
    -0.08
    驱
    -0.08
    uma
    -0.08
    POSITIVE LOGITS
    éħ£
    0.10
    å®īä¿Ŀ
    0.10
    æĬ¢åĬ«
    0.09
    éĵ¤
    0.09
    çıłå®Ŀ
    0.09
    审
    0.09
    ystore
    0.09
    è£ħå¤ĩ
    0.09
    çŃĸåĪĴ
    0.09
    ollo
    0.08
    Activations Density 0.127%

    No Known Activations