© 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. 53512
    Prev
    Next
    INDEX
    Explanations

    stay tuned for

    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
    è¦ģåľ¨
    -0.10
    磶
    -0.10
    å¾Īåĸľæ¬¢
    -0.09
    æĶ¾è¿Ľ
    -0.08
    oke
    -0.08
    äºĨåĩºæĿ¥
    -0.08
    æīĢ以说
    -0.08
    è§Ī
    -0.08
    Streamer
    -0.08
    andbox
    -0.08
    POSITIVE LOGITS
    åıijå±ķè§ĦåĪĴ
    0.10
    VERS
    0.09
    led
    0.09
    Soap
    0.09
    以ä¸ĭ
    0.09
    erna
    0.08
    以ä¸ĭåĩłä¸ª
    0.08
    èķ¤
    0.08
    ä¸ĭ称
    0.08
    _salt
    0.08
    Activations Density 0.007%

    No Known Activations