© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10359
    Prev
    Next
    INDEX
    Explanations

    bugs and insects

    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
    anes
    -0.08
    edList
    -0.08
     Cumberland
    -0.08
    qual
    -0.08
    ä¸Ģ人
    -0.08
    强迫
    -0.08
     Vall
    -0.08
    åĪĥ
    -0.08
    QUAL
    -0.08
    çŀĦ
    -0.08
    POSITIVE LOGITS
    èĻ«
    0.20
    èŁ²
    0.16
    æĺĨèĻ«
    0.14
    BUG
    0.14
    bug
    0.14
     insects
    0.13
    èĿĹ
    0.13
    ðŁIJĽ
    0.13
     bugs
    0.13
    Bug
    0.13
    Activations Density 0.054%

    No Known Activations