© 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. 31079
    Prev
    Next
    INDEX
    Explanations

    ignition system components and operation

    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
    èī¯å¿ĥ
    -0.10
    ä¹ł
    -0.10
    æĿĥ
    -0.09
    xic
    -0.09
    _HEAP
    -0.08
    หาร
    -0.08
    éĢł
    -0.08
    بت
    -0.08
    ä¸İåħ¶ä»ĸ
    -0.08
     mor
    -0.08
    POSITIVE LOGITS
    itm
    0.10
    èĢĢ
    0.10
    çŀ¿
    0.10
     INCLUDED
    0.10
    ipple
    0.09
    çħĬ
    0.09
    çĩİ
    0.09
    æĢ§åĪ«
    0.09
    /Area
    0.09
    çīĿ
    0.09
    Activations Density 0.054%

    No Known Activations