© 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. 23148
    Prev
    Next
    INDEX
    Explanations

    distances and origins

    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
    èļĮ
    -0.10
    _pb
    -0.10
    rics
    -0.09
    åĬ©æīĭ
    -0.09
    least
    -0.09
    ä¹ĭ乡
    -0.09
    æľ¨èĢ³
    -0.09
    ÑĢож
    -0.09
    åħħåĢ¼
    -0.09
     пÑģ
    -0.09
    POSITIVE LOGITS
     visible
    0.11
    åı¯è§ģ
    0.11
    è¿ľå¤Ħ
    0.10
    å°±æĥ³
    0.10
    visible
    0.10
    åı¯è§Ĩ
    0.09
    Visible
    0.09
    æľĽ
    0.09
    è¿ľè¿ľ
    0.09
    æĸ¹åľĨ
    0.09
    Activations Density 0.176%

    No Known Activations