© 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. 11458
    Prev
    Next
    INDEX
    Explanations

    bicycle and cycle 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
    ANCH
    -0.10
    anch
    -0.10
    _rom
    -0.09
    åĭŁ
    -0.09
    _placement
    -0.09
    å¾Īæĥ³
    -0.09
    anco
    -0.09
    ä¹Ķ
    -0.09
    涯
    -0.09
    :NS
    -0.09
    POSITIVE LOGITS
    èĩªè¡Į车
    0.15
    éªijè¡Į
    0.15
     bike
    0.15
     bicycle
    0.14
    éªij
    0.13
    icycle
    0.11
     bicycles
    0.11
     Bike
    0.11
    çĶµåĬ¨è½¦
    0.10
    æij©æīĺ车
    0.10
    Activations Density 0.077%

    No Known Activations