© 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. 10789
    Prev
    Next
    INDEX
    Explanations

    prey and predators

    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
    è´Łè´£ä»»
    -0.09
    ov
    -0.09
    ince
    -0.09
    uju
    -0.09
    пÑĥ
    -0.09
    èijŃ
    -0.09
    èĻ¢
    -0.08
    ichel
    -0.08
    itra
    -0.08
    ãģ¦ãĤĤ
    -0.08
    POSITIVE LOGITS
    IES
    0.09
    ackage
    0.09
    renc
    0.09
    auge
    0.08
    eric
    0.08
    å¾Ĺä½ı
    0.08
    edBy
    0.08
    ello
    0.08
     Shim
    0.08
    manship
    0.08
    Activations Density 0.037%

    No Known Activations