© 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. 16466
    Prev
    Next
    INDEX
    Explanations

    grip strength

    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
    çĪº
    -0.18
    hood
    -0.17
    ogue
    -0.17
    hel
    -0.17
    è¡ĮæĶ¿éĥ¨éŨ
    -0.16
    eph
    -0.16
    éľı
    -0.16
    fram
    -0.16
    bery
    -0.15
    èİĵ
    -0.15
    POSITIVE LOGITS
     ÑĩаÑģ
    0.18
    ä½ıäºĨ
    0.18
    ters
    0.18
    ÑĩаÑģ
    0.18
    å¤§èµĽ
    0.17
    abble
    0.17
    丧失
    0.17
    ä¸İæŶ
    0.17
    amer
    0.16
    çħ
    0.16
    Activations Density 0.005%

    No Known Activations