© 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. 33923
    Prev
    Next
    INDEX
    Explanations

    latitude and longitude

    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
    ¢åįķ
    -0.09
    åį«è§Ĩ
    -0.09
    ria
    -0.08
    mental
    -0.08
    ìĤ´
    -0.08
    çıĢ
    -0.08
    建åħļ
    -0.08
    odge
    -0.08
    eld
    -0.08
    ong
    -0.08
    POSITIVE LOGITS
    (lat
    0.13
    -lat
    0.10
    elier
    0.10
    RAL
    0.10
     ÑĥÑģи
    0.09
     lat
    0.09
     Lat
    0.09
    ITUDE
    0.09
    istic
    0.09
    鸶
    0.09
    Activations Density 0.045%

    No Known Activations