© 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. 50865
    Prev
    Next
    INDEX
    Explanations

    Henry VII, Catherine

    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
    å¿ĥ缮
    -0.10
    ackbar
    -0.10
    ä¸Ĭå²Ĺ
    -0.09
    éķ¿çĽ¸
    -0.09
    óst
    -0.09
    лик
    -0.09
     Jail
    -0.09
    èĮĦ
    -0.09
    åĨĽåĽ¢
    -0.09
    _SD
    -0.09
    POSITIVE LOGITS
     Wald
    0.09
    åłĨ
    0.09
    bis
    0.09
    å¤ļéĩį
    0.09
     Chow
    0.08
    scoped
    0.08
    -arrow
    0.08
    ocha
    0.08
    _checked
    0.08
    åıĮéĩį
    0.08
    Activations Density 0.126%

    No Known Activations