© 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. 34214
    Prev
    Next
    INDEX
    Explanations

    revert to, resort to, reverted to

    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
    示èĮĥåŁºåľ°
    -0.10
    姣
    -0.09
    ŀ
    -0.09
    ива
    -0.08
    paced
    -0.08
    æĢİä¹ĪåĽŀäºĭ
    -0.08
    hatt
    -0.08
    /rfc
    -0.08
    å¿¡
    -0.08
    ancing
    -0.08
    POSITIVE LOGITS
    åıªèĥ½è¯´
    0.11
    åķ¬
    0.10
    idor
    0.09
    ents
    0.09
    ocha
    0.08
    天河
    0.08
    åijĹ
    0.08
    æŀģ端
    0.08
    ajo
    0.08
    çļĦåĬŀæ³ķ
    0.08
    Activations Density 0.012%

    No Known Activations