© 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. 27974
    Prev
    Next
    INDEX
    Explanations

    sponsors and sponsorship

    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
    èĢģ人家
    -0.09
    æľĢéĢĤåIJĪ
    -0.09
    ãĥ¥
    -0.09
    ä»ħ次äºİ
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.09
    社ä¼ļæķĪçĽĬ
    -0.09
    åĶ¯æľī
    -0.09
    累累
    -0.09
    OwnProperty
    -0.09
    ä»»ä½ķ人éĥ½
    -0.08
    POSITIVE LOGITS
    ship
    0.15
    ships
    0.15
    å¨ĺ
    0.11
    ned
    0.10
    ctl
    0.10
    ëĭĺ
    0.10
    ëĦIJ
    0.09
    ably
    0.09
    iled
    0.09
    atory
    0.09
    Activations Density 0.011%

    No Known Activations