© 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. 31927
    Prev
    Next
    INDEX
    Explanations

    terrain and topography

    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
    åĽ¢ä½ĵ
    -0.10
    笼
    -0.09
    çĻ½èī²çļĦ
    -0.09
    å¥ĹæĪ¿
    -0.09
     Lazar
    -0.09
    white
    -0.08
    ãģ£ãģĵ
    -0.08
     Infinity
    -0.08
    å»ī
    -0.08
    çĽı
    -0.08
    POSITIVE LOGITS
    åľ°å½¢
    0.17
    åľ°è²Į
    0.14
     terrain
    0.14
     Terrain
    0.13
    å´İ
    0.12
    èµ·ä¼ı
    0.12
    geist
    0.10
    éļľç¢į
    0.10
    å²ĸ
    0.10
    å¹³åĿ¦
    0.10
    Activations Density 0.050%

    No Known Activations