© 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. 30906
    Prev
    Next
    INDEX
    Explanations

    my or your followed by a noun

    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
    èĴ¿
    -0.12
    è··
    -0.11
     ÑĢанее
    -0.10
     давно
    -0.09
    lander
    -0.09
    ä¸įè§ģäºĨ
    -0.09
     waż
    -0.09
    specs
    -0.09
    åħ»èĤ²
    -0.09
    à¸Ńาà¸Ī
    -0.09
    POSITIVE LOGITS
     to
    0.12
     able
    0.10
    å°½åı¯èĥ½
    0.09
    Near
    0.09
    æľĢç»Ī
    0.08
    umble
    0.08
    æĶ¯æı´
    0.08
    åIJĥçļĦ
    0.08
    åĬłæĮģ
    0.08
     знаÑĤÑĮ
    0.08
    Activations Density 0.055%

    No Known Activations