© 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. 10746
    Prev
    Next
    INDEX
    Explanations

    finding out or learning

    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
    åĩ«
    -0.11
    æĦŁåı¹
    -0.10
    ncmp
    -0.09
    ä¸įæİĴéĻ¤
    -0.09
    _DER
    -0.09
    afone
    -0.09
    isphere
    -0.09
    _mes
    -0.09
    åĿĬ
    -0.09
    afari
    -0.08
    POSITIVE LOGITS
    å¾ĹçŁ¥
    0.20
    äºĨ解åĪ°
    0.18
    èİ·æĤī
    0.16
    çľĭåĪ°
    0.15
    åIJ¬è¯´
    0.14
    çŁ¥éģĵäºĨ
    0.13
    è§ģåĪ°
    0.13
    çľĭè§ģ
    0.12
    认è¯ĨåĪ°
    0.11
    çŁ¥éģĵ
    0.11
    Activations Density 0.043%

    No Known Activations