© 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. 20076
    Prev
    Next
    INDEX
    Explanations

    distance measurement ultrasonic sensors

    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
    åıĹçIJĨ
    -0.10
    åħ¥åľº
    -0.09
     pinch
    -0.09
    æľŁæľĽ
    -0.09
    è¿ĩ渡
    -0.08
    è¿Ľåľº
    -0.08
    绣çŃ¹
    -0.08
    ç¿İ
    -0.08
     Kathy
    -0.08
    æĻķ
    -0.08
    POSITIVE LOGITS
    è·ĭ
    0.11
    è·
    0.11
    å¾Ģè¿Ķ
    0.10
    æĬĬæĪij
    0.09
    çļĦèĦļæŃ¥
    0.09
     ÑĤÑĥ
    0.09
    éķ¿çŁŃ
    0.09
    _echo
    0.09
    lier
    0.09
    ä¼Ĺ
    0.09
    Activations Density 0.096%

    No Known Activations