© 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. 13405
    Prev
    Next
    INDEX
    Explanations

    angling, hunting, recreational

    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
    ä»·éĴ±
    -0.20
    dance
    -0.18
    OfWork
    -0.18
    _CALL
    -0.18
     labour
    -0.18
    è¯Ħæ¯Ķ
    -0.18
    纪å§Ķ书记
    -0.18
    _called
    -0.18
    instances
    -0.17
     callee
    -0.17
    POSITIVE LOGITS
    éĺŁä¼į
    0.21
    大åĨĽ
    0.21
    å°Ŀ
    0.20
    èĽİ
    0.20
    ä¹ĭå¿ĥ
    0.20
     Citizen
    0.19
    åħ¬æ°ij
    0.19
    ä¹łæĥ¯
    0.19
    -friendly
    0.19
    innen
    0.18
    Activations Density 0.008%

    No Known Activations