© 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. 38209
    Prev
    Next
    INDEX
    Explanations

    window glass

    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
    cul
    -0.10
    æľīå¾ħ
    -0.09
    èĨ¨èĥĢ
    -0.09
    è¯ļ
    -0.09
    ä¸ĩ家
    -0.08
     IMO
    -0.08
    åħ±æľī
    -0.08
    gro
    -0.08
    å²ģ以ä¸Ĭ
    -0.08
    atica
    -0.08
    POSITIVE LOGITS
     ì²ĺ
    0.11
    çijķ
    0.10
    çªĹæĪ·
    0.09
    è¼Ķ
    0.09
    åį°
    0.09
    çİ»çĴĥ
    0.09
    è¾ħ
    0.09
    é£İåı£
    0.09
    çĻ¾ç§ij
    0.09
    åīįç½®
    0.09
    Activations Density 0.084%

    No Known Activations