© 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. 30434
    Prev
    Next
    INDEX
    Explanations

    Nissan launches

    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
    ew
    -0.10
    å¡ĺ
    -0.10
    ens
    -0.10
    ×ķת
    -0.09
     Laden
    -0.09
    ä¸įæ¸ħæ¥ļ
    -0.09
    åľ¹
    -0.08
    åĩ¡æľ¬ç½ij
    -0.08
    åı£å¾Ħ
    -0.08
    çĸ³
    -0.08
    POSITIVE LOGITS
    pei
    0.10
     оÑĤз
    0.10
    ลà¸ļ
    0.09
    åħħ足çļĦ
    0.09
    oseconds
    0.09
    ØŃ
    0.08
    pth
    0.08
    ç¥Ĺ
    0.08
    祺
    0.08
     اÙĦأخ
    0.08
    Activations Density 0.002%

    No Known Activations