© 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. 57814
    Prev
    Next
    INDEX
    Explanations

    biological sequences and sequencing

    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
    åı¦ä¸Ģä½į
    -0.09
    ä¸įçķĻ
    -0.09
    als
    -0.09
    æ²Ķ
    -0.08
    ëĿ½
    -0.08
    lator
    -0.08
    èĢĥçĤ¹
    -0.08
    elsey
    -0.08
    è¿ĩäºİ
    -0.08
    _MISSING
    -0.08
    POSITIVE LOGITS
    éĨį
    0.09
    æľīæĦıä¹ī
    0.09
     spot
    0.09
    å¸Ńåį·
    0.09
    åĪ¨
    0.09
    æłª
    0.09
    éĢı
    0.09
    DataURL
    0.09
    CAPE
    0.09
     illum
    0.08
    Activations Density 0.212%

    No Known Activations