© 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. 32407
    Prev
    Next
    INDEX
    Explanations

    study 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
    è¿ijäºĽ
    -0.09
    oter
    -0.09
    ÐĶаÑĤа
    -0.09
    å°±è§īå¾Ĺ
    -0.08
    æĺ¯éĿŀ
    -0.08
    姻
    -0.08
    è¿ijå¹´æĿ¥
    -0.08
    è¦ĭãģ¦
    -0.08
     Dag
    -0.08
    åıĥ
    -0.08
    POSITIVE LOGITS
    èĢĥéªĮ
    0.09
    大èĥĨ
    0.09
    å±ĢéĿ¢
    0.09
    åĬłæ²¹
    0.09
    æĶ¾å®½
    0.09
    å®ļåIJij
    0.09
    å¨ģèĥģ
    0.09
    cred
    0.09
    å¤§éĽ¨
    0.08
    Stretch
    0.08
    Activations Density 0.025%

    No Known Activations