© 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. 3631
    Prev
    Next
    INDEX
    Explanations

    use of resources and skills

    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
    没æĶ¶
    -0.10
    æ°ijå¿ĥ
    -0.08
    çĶĺ
    -0.08
    æľīä¿¡å¿ĥ
    -0.08
    uv
    -0.08
    ivo
    -0.08
    ạn
    -0.08
    çİĭçīĮ
    -0.08
    åħ±
    -0.08
    åĪ¤å®ļ
    -0.08
    POSITIVE LOGITS
    æĬĬèĩªå·±
    0.09
     herself
    0.09
    å¤ļç§į
    0.09
    bourg
    0.08
    å¤ļæł·æĢ§
    0.08
     Caval
    0.08
    /ws
    0.08
    ocket
    0.08
    æĹºçĽĽ
    0.08
     lif
    0.08
    Activations Density 0.013%

    No Known Activations