© 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. 33875
    Prev
    Next
    INDEX
    Explanations

    devices and components

    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
    ãģ¾ãģ¾
    -0.10
    éĹº
    -0.09
    æĶ¶åħ¥
    -0.09
    åŃĺåľ¨äºİ
    -0.09
    èĢĥåľº
    -0.08
    erk
    -0.08
    ness
    -0.08
     benches
    -0.08
    lash
    -0.08
    town
    -0.08
    POSITIVE LOGITS
    ä¸ŃçļĦ
    0.15
    ä¸Ńæĸ°
    0.11
    éĩĮçļĦ
    0.10
    åŃIJéĩĮ
    0.10
    æĪIJè´¥
    0.10
    ä¸Ńæľī
    0.09
    ä¸Ńåħ±
    0.09
    éģĵçIJĨ
    0.09
    è¦ģçĶ¨
    0.09
    ãģ«ãģĬãģijãĤĭ
    0.09
    Activations Density 1.005%

    No Known Activations