© 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. 30625
    Prev
    Next
    INDEX
    Explanations

    all the references

    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
    ä¸Ģå¤ľ
    -0.10
    åĪ¶æŃ¢
    -0.09
    马
    -0.09
    éĶµ
    -0.09
    UNS
    -0.08
    çŀ¬éĹ´
    -0.08
     Noel
    -0.08
    éĢĤå®ľ
    -0.08
    åĮ¾
    -0.08
    ạo
    -0.08
    POSITIVE LOGITS
    èĬĤçľģ
    0.10
    åĨµä¸Ķ
    0.09
    ledon
    0.09
    åĩłçĤ¹
    0.09
    (Func
    0.09
    æŃ£å¸¸ä½¿çĶ¨
    0.09
    æĪIJ绩
    0.09
    æľīåĪ©
    0.09
    ç¹
    0.08
    ä½ķåĨµ
    0.08
    Activations Density 0.026%

    No Known Activations