© 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. 23755
    Prev
    Next
    INDEX
    Explanations

    fuel injection

    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
    odynam
    -0.09
    onta
    -0.09
    ắc
    -0.08
    é¾ĻéŨ
    -0.08
    atile
    -0.08
    ÙĪÙĬد
    -0.08
    aina
    -0.08
    齿
    -0.08
     brought
    -0.08
    _strike
    -0.08
    POSITIVE LOGITS
    pio
    0.10
     Pompeo
    0.09
    æļ
    0.09
    ç±³ç²ī
    0.09
     poo
    0.09
    祸
    0.09
    æĪ¿ä¸ľ
    0.08
    èµģ
    0.08
    .Packet
    0.08
    maze
    0.08
    Activations Density 0.097%

    No Known Activations