© 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. 30662
    Prev
    Next
    INDEX
    Explanations

    ArcGIS, GIS Enterprise, javascript API

    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
    æľ¬åĽ½
    -0.09
    åİī
    -0.09
    mere
    -0.09
    è¯Ńè¨Ģ
    -0.09
    çľ¾
    -0.09
    erval
    -0.09
    æľīåĪ©
    -0.09
    anguage
    -0.08
    orm
    -0.08
    tc
    -0.08
    POSITIVE LOGITS
    <![
    0.09
    nds
    0.09
    ettes
    0.08
    ÑĢай
    0.08
    yms
    0.08
    PF
    0.08
    UCT
    0.08
    èĺħ
    0.08
    haft
    0.08
     singleton
    0.08
    Activations Density 0.005%

    No Known Activations