© 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. 63124
    Prev
    Next
    INDEX
    Explanations

    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
     Hague
    -0.10
    èı½
    -0.09
    etrain
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
     INCLUDED
    -0.09
    ÑĤелÑĮ
    -0.09
     вÑģÑı
    -0.09
    .toBe
    -0.09
    å¤ĸè§Ĥ
    -0.09
    ulan
    -0.08
    POSITIVE LOGITS
     track
    0.21
    è·Łè¸ª
    0.19
     Track
    0.18
    追踪
    0.18
    track
    0.17
    .track
    0.17
    踪
    0.16
    -track
    0.16
     tracking
    0.16
    (track
    0.16
    Activations Density 0.099%

    No Known Activations