© 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. 61486
    Prev
    Next
    INDEX
    Explanations

    places to stay

    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
    vinc
    -0.09
    常æĢģåĮĸ
    -0.08
    nj
    -0.08
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.08
    plat
    -0.08
    riers
    -0.08
    å®´
    -0.08
    olen
    -0.08
    æī¶
    -0.08
    _hyper
    -0.08
    POSITIVE LOGITS
    ä¿¡
    0.10
    æľ´å®ŀ
    0.09
    æīĥ
    0.09
    éĿłè¿ij
    0.09
    æºIJæ³ī
    0.08
    åľ¨å½ĵåľ°
    0.08
    áĥ«
    0.08
    èĩªåĬ©
    0.08
    æĬķ
    0.08
    ç²¹
    0.08
    Activations Density 0.051%

    No Known Activations