© 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. 37657
    Prev
    Next
    INDEX
    Explanations

    road entry or shops

    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
    åľ¨åºĬä¸Ĭ
    -0.11
    ree
    -0.09
     Morr
    -0.09
    åĿ¨
    -0.09
    åĬ©
    -0.09
    éĨ´
    -0.09
    è¢į
    -0.09
    大å±Ģ
    -0.09
    åĨįéĢł
    -0.09
    ÑĢаÐ
    -0.09
    POSITIVE LOGITS
    å··
    0.14
    åĪĨæĶ¯
    0.13
    å²Ķ
    0.12
    ä¸īæĿ¡
    0.11
    èĥ¡åIJĮ
    0.11
     alley
    0.11
    è¡Ĺ
    0.10
    åĪĨæµģ
    0.10
    è·¯åı£
    0.10
    éģĵ
    0.10
    Activations Density 0.062%

    No Known Activations