© 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. 12964
    Prev
    Next
    INDEX
    Explanations

    certain degree

    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
     wed
    -0.24
    wed
    -0.21
    _POWER
    -0.18
    éĢł
    -0.18
    _power
    -0.18
    tra
    -0.18
    è´©
    -0.17
    _flg
    -0.17
    Power
    -0.17
    Wed
    -0.17
    POSITIVE LOGITS
     Vac
    0.21
    born
    0.21
    äºĴåĪ©
    0.20
    æĺŁå·´
    0.20
    alla
    0.20
     born
    0.19
     Suzuki
    0.19
    à¦Ł
    0.19
    认åı¯
    0.19
    çļĦ认åı¯
    0.18
    Activations Density 0.411%

    No Known Activations