© 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. 54263
    Prev
    Next
    INDEX
    Explanations

    Association of

    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
     unt
    -0.09
    ä¸Ģèīĺ
    -0.08
    IENT
    -0.08
    工信éĥ¨
    -0.08
    ä¸Ģè¾Ĩ
    -0.08
    åħ¶ä½Ļ
    -0.08
    ike
    -0.07
    agen
    -0.07
    æ²»çĹħ
    -0.07
    ursive
    -0.07
    POSITIVE LOGITS
    强æľīåĬĽçļĦ
    0.10
    lia
    0.10
    åݿ级
    0.10
    åħ¨æĹ¥åĪ¶
    0.09
     cứ
    0.09
    åł¡åŀĴ
    0.09
    å®īéĿĻ
    0.09
    诸侯
    0.09
    ento
    0.09
    æµģåĩº
    0.09
    Activations Density 0.019%

    No Known Activations