© 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. 32937
    Prev
    Next
    INDEX
    Explanations

    phase II clinical trials

    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
    èĩªåıij
    -0.10
    acci
    -0.10
    çŃĽæŁ¥
    -0.10
    å®Ī
    -0.09
     imper
    -0.09
    西è£ħ
    -0.09
    èĸĽ
    -0.09
    ì§ģ
    -0.09
    ott
    -0.09
     indirect
    -0.08
    POSITIVE LOGITS
    æĬķæľº
    0.10
    éĴµ
    0.09
    è¡Ķ
    0.09
    ?option
    0.09
    .setMax
    0.09
    å°ĸ
    0.08
    _coin
    0.08
    è¿ijæľŁ
    0.08
    .ga
    0.08
    æİī
    0.08
    Activations Density 0.158%

    No Known Activations