© 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. 55954
    Prev
    Next
    INDEX
    Explanations

    if... you or fine... too

    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
    çĻŀ
    -0.09
    ny
    -0.09
    .appspot
    -0.09
    çĸ½
    -0.09
    _lift
    -0.09
     вÑĭп
    -0.08
     Lift
    -0.08
    çĪ¬
    -0.08
    ë²
    -0.08
    oled
    -0.08
    POSITIVE LOGITS
    åģļä¸įåĪ°
    0.12
    说èĩªå·±
    0.10
     imper
    0.09
    ä¸ĢæŶ
    0.09
    Ùħر
    0.09
    åıįå¤į
    0.09
    åŃ£
    0.09
    è¿Ļåıª
    0.09
    èı°
    0.09
    ç§
    0.09
    Activations Density 0.033%

    No Known Activations