© 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. 53408
    Prev
    Next
    INDEX
    Explanations

    predation, prey, insects, catch, hunt

    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
    æ¼ıæ°´
    -0.10
    åĬ²
    -0.09
    _Output
    -0.09
    éºĹ
    -0.09
    é©´
    -0.09
    eworld
    -0.09
    bv
    -0.09
    .lv
    -0.09
    çĶŁåij½åĬĽ
    -0.09
    dims
    -0.08
    POSITIVE LOGITS
     Flake
    0.09
    èĻ«
    0.09
    .dy
    0.09
    pie
    0.09
    oped
    0.08
    inho
    0.08
    ä¼ĺè´¨
    0.08
    躬
    0.08
    飦
    0.08
     insects
    0.08
    Activations Density 0.028%

    No Known Activations