© 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. 56095
    Prev
    Next
    INDEX
    Explanations

    roadside and surrounding areas

    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
    æ¶Ī
    -0.09
    驾
    -0.09
    çŀİ
    -0.09
    æĵĢ
    -0.09
    imax
    -0.09
    æ¿¡
    -0.09
    ç²ľ
    -0.08
    å¿ĥè¡Ģ
    -0.08
    oplan
    -0.08
    cg
    -0.08
    POSITIVE LOGITS
    路边
    0.16
     roadside
    0.13
    side
    0.11
    ROAD
    0.11
     road
    0.10
     side
    0.10
     доÑĢог
    0.10
    éģĵè·¯
    0.10
    .Side
    0.09
    доÑĢож
    0.09
    Activations Density 0.212%

    No Known Activations