© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8786
    Prev
    Next
    INDEX
    Explanations

    fire and its impact

    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
    è®¤çľŁåŃ¦ä¹ł
    -0.09
    å·¥
    -0.08
    leÅŁ
    -0.08
    岫
    -0.08
    \Array
    -0.08
    perm
    -0.07
    <![
    -0.07
     CM
    -0.07
     STUD
    -0.07
    æ¦ľ
    -0.07
    POSITIVE LOGITS
    adge
    0.10
    éº
    0.10
    å¤ļå±Ĥ次
    0.09
    _SF
    0.09
    羣å®ŀ
    0.09
    -ish
    0.09
    ForObject
    0.08
    éŵ
    0.08
    èĪĴå¿ĥ
    0.08
    MAL
    0.08
    Activations Density 0.623%

    No Known Activations