© 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. 61975
    Prev
    Next
    INDEX
    Explanations

    GPS and location tracking

    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
    åİħ
    -0.12
    .libs
    -0.10
     Robots
    -0.09
    ä»ĺåĩº
    -0.09
    hall
    -0.09
    廳
    -0.09
     hallway
    -0.08
    èĬ±çĶŁ
    -0.08
    大åİħ
    -0.08
    velle
    -0.08
    POSITIVE LOGITS
     GPS
    0.16
    åĮĹæĸĹ
    0.13
     gps
    0.12
    gps
    0.12
    GPS
    0.12
    ç»ı纬
    0.11
    å®ļä½į
    0.11
    çĽij
    0.11
    精度
    0.10
    _gps
    0.10
    Activations Density 0.113%

    No Known Activations