© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15930
    Prev
    Next
    INDEX
    Explanations

    saying or asking something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    _bridge
    -0.20
    ÑıÑģ
    -0.20
    _LINEAR
    -0.19
    ForKey
    -0.19
    OLD
    -0.19
    æĻ¤
    -0.19
    修订
    -0.19
    shared
    -0.19
    _latency
    -0.19
    -shared
    -0.18
    POSITIVE LOGITS
    ä»ĸ人
    0.24
    说æĪij
    0.21
     suddenly
    0.20
    ibo
    0.20
    ior
    0.19
    说èĩªå·±
    0.19
     hypoc
    0.19
    æĮĩè´£
    0.19
     EVER
    0.19
     Bernstein
    0.19
    Activations Density 0.011%

    No Known Activations