© 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. 28152
    Prev
    Next
    INDEX
    Explanations

    wheel related concepts

    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
    çªĸ
    -0.09
    она
    -0.09
    oken
    -0.09
    ä¸Ģç¬Ķ
    -0.09
    段
    -0.09
    yal
    -0.08
     communicator
    -0.08
    åĺ¹
    -0.08
    elle
    -0.08
    å¼łæī¬
    -0.08
    POSITIVE LOGITS
    wheel
    0.15
     wheels
    0.13
     wheel
    0.12
    Wheel
    0.12
     Wheel
    0.11
    è½®
    0.11
    -wheel
    0.11
     Wheels
    0.11
    è¾ĭ
    0.10
     tire
    0.10
    Activations Density 0.034%

    No Known Activations