© 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. 4500
    Prev
    Next
    INDEX
    Explanations

    combustion engine components

    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
     Dexter
    -0.09
    èµ°å¾Ĺ
    -0.09
    å°Ŀè¯ķ
    -0.08
    é¹ħ
    -0.08
    离
    -0.08
    ORED
    -0.08
    ackets
    -0.08
    èŁĴ
    -0.08
    æĿĸ
    -0.08
    _unused
    -0.08
    POSITIVE LOGITS
    Injected
    0.09
    è´Łè´£åIJĮå¿Ĺ
    0.09
    åıijåĬ¨æľº
    0.09
    ä¼Ĺ
    0.09
    CA
    0.09
     Kemp
    0.08
    åļ¼
    0.08
    éªĹåıĸ
    0.08
    CCI
    0.08
    è¿Ļæī¹
    0.08
    Activations Density 0.090%

    No Known Activations