© 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. 33279
    Prev
    Next
    INDEX
    Explanations

    overcoming obstacles and difficulties

    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
    åĪĨ辨
    -0.10
    çĿĢæĢ¥
    -0.09
    pear
    -0.09
    æįħ
    -0.09
    è·Łè¿Ľ
    -0.09
    -pic
    -0.09
    çĭİ
    -0.08
    zn
    -0.08
    éģµå¾ª
    -0.08
    触
    -0.08
    POSITIVE LOGITS
    éļľç¢į
    0.12
    æĿŁç¼ļ
    0.12
    éļ¾åħ³
    0.12
    æ¡İ
    0.11
    åł¡åŀĴ
    0.11
    ä¸ĢéĿ¢
    0.10
    害ç¾ŀ
    0.10
     barriers
    0.10
    æĿ¥çľĭçľĭ
    0.10
    éĩįéĩį
    0.10
    Activations Density 0.035%

    No Known Activations