© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53043
    Prev
    Next
    INDEX
    Explanations

    RBI, RS!, name, ERA

    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
    èģĨ
    -0.09
    å±ī
    -0.09
    burg
    -0.09
    ality
    -0.09
    _fname
    -0.08
     Hick
    -0.08
    ä¹Łä¸įæĥ³
    -0.08
    auty
    -0.08
    spy
    -0.08
    AIT
    -0.08
    POSITIVE LOGITS
    å¾ģ
    0.10
    楯
    0.09
    oru
    0.09
    åľ°çIJĨ
    0.09
    æ¦ľ
    0.09
    éĥİ
    0.08
    ðŁĴ»
    0.08
    åĢĴ
    0.08
    èĭ§
    0.08
    æĬ¥åijĬæľŁåĨħ
    0.08
    Activations Density 0.001%

    No Known Activations