© 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. 51085
    Prev
    Next
    INDEX
    Explanations

    horror, wilderness, terror, hate

    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
    zelf
    -0.11
    TING
    -0.10
    sWith
    -0.10
    ä¸įä¸Ĭ
    -0.09
    ucer
    -0.09
     surre
    -0.09
    .copyOf
    -0.08
    æĿ¥ä¸įåıĬ
    -0.08
    åĦ¿
    -0.08
    uman
    -0.08
    POSITIVE LOGITS
    oso
    0.13
    fully
    0.11
    ously
    0.11
    ful
    0.11
    iest
    0.10
    FUL
    0.10
    cly
    0.09
    ous
    0.09
     seekers
    0.08
    ÑīÑĥ
    0.08
    Activations Density 0.049%

    No Known Activations