© 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. 61727
    Prev
    Next
    INDEX
    Explanations

    white rabbits

    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¢ĸ
    -0.08
    迤
    -0.08
    æĭĵ
    -0.08
    åħ¨æĻ¯
    -0.08
    èĪĢ
    -0.08
    eller
    -0.08
    ended
    -0.08
    ç»Ń
    -0.08
    æĵİ
    -0.08
     grave
    -0.08
    POSITIVE LOGITS
    åħĶåŃIJ
    0.12
    rabbit
    0.11
    åħĶ
    0.11
    è·³è·ĥ
    0.11
    åĬŁ
    0.11
    é¾Ł
    0.10
    大èħ¿
    0.10
    quine
    0.10
    é³
    0.10
     rabbit
    0.10
    Activations Density 0.058%

    No Known Activations