© 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. 38801
    Prev
    Next
    INDEX
    Explanations

    fire related compounds

    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
    ities
    -0.11
    ooter
    -0.10
    arian
    -0.09
    ÙĪÙĬØ©
    -0.09
    ions
    -0.09
    æ¦Ī
    -0.09
    recht
    -0.09
    rss
    -0.09
    æĶ¾æīĭ
    -0.09
    uration
    -0.08
    POSITIVE LOGITS
    fully
    0.15
    banks
    0.10
    places
    0.10
    lectric
    0.10
    nze
    0.10
    flies
    0.10
    fulness
    0.09
    baugh
    0.09
    åħįéĻ¤
    0.09
    fighter
    0.09
    Activations Density 0.036%

    No Known Activations