© 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. 36415
    Prev
    Next
    INDEX
    Explanations

    card or cards

    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
    çľŁç©º
    -0.08
    æī¿åĮħ
    -0.08
    åģ·
    -0.08
    çĨŁ
    -0.08
    æIJŃæ¡£
    -0.08
     impress
    -0.08
    бед
    -0.08
    ä¸Ĭåij¨
    -0.08
    ptime
    -0.08
    redi
    -0.08
    POSITIVE LOGITS
    磾
    0.11
    åį¡çīĩ
    0.11
    åĨĻä½ľ
    0.10
    /Library
    0.09
    .Library
    0.09
    è°Ģ
    0.09
    ä¹ĸ
    0.09
    ede
    0.09
    åıįè¿ĩæĿ¥
    0.09
    è¿·
    0.08
    Activations Density 0.038%

    No Known Activations