© 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. 7538
    Prev
    Next
    INDEX
    Explanations

    fear, spiders, and fright

    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
    çIJIJ
    -0.10
     frustration
    -0.10
     frustr
    -0.10
     frustrations
    -0.09
    ä¸įçĶ±
    -0.09
    anvas
    -0.09
    enheim
    -0.08
     Dish
    -0.08
     Ñģв
    -0.08
     Canvas
    -0.08
    POSITIVE LOGITS
    æģIJæĥ§
    0.16
    åĭĩæķ¢
    0.14
    æģIJæĢĸ
    0.14
    æĢĸ
    0.13
    害æĢķ
    0.13
    èĥĨ
    0.13
    æģIJæħĮ
    0.11
    åIJĵ
    0.11
    åIJĵå¾Ĺ
    0.11
    æĥ§
    0.11
    Activations Density 0.104%

    No Known Activations