© 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. 62057
    Prev
    Next
    INDEX
    Explanations

    dense vegetation

    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
    åĭ¤
    -0.10
    ords
    -0.10
    ç²ī
    -0.10
    éĿ¥
    -0.10
    èļĮ
    -0.10
    èĩ´
    -0.09
    鱿
    -0.09
    çļĵ
    -0.09
    饫
    -0.09
    çģ¶
    -0.09
    POSITIVE LOGITS
    丼
    0.14
    æ£īèĬ±
    0.10
    èĮĤ
    0.10
    æ¤į被
    0.10
     ent
    0.09
     bushes
    0.09
     Eck
    0.09
    غÙħ
    0.09
     branches
    0.08
    oger
    0.08
    Activations Density 0.184%

    No Known Activations