© 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. 30772
    Prev
    Next
    INDEX
    Explanations

    animal locomotion and body parts

    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
     ÑįÑĤим
    -0.11
    ully
    -0.09
    æĬ¬å¤´
    -0.09
    æľīåħ´è¶£
    -0.09
     Ñģобой
    -0.08
    å±ł
    -0.08
     Hamm
    -0.08
     Rei
    -0.08
    _VC
    -0.08
    æµĬ
    -0.08
    POSITIVE LOGITS
    èħ³
    0.11
    è¹Ħ
    0.10
    踩
    0.10
    è¸ı
    0.10
    åĮĨ
    0.09
    èĦļæŃ¥
    0.09
    æŃ¥ä¼IJ
    0.09
    éªij
    0.09
    æ·¹
    0.09
    ä¸ĢèĦļ
    0.09
    Activations Density 0.055%

    No Known Activations