© 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. 14451
    Prev
    Next
    INDEX
    Explanations

    wifi and summer months

    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
    åĪ°æľĢåIJİ
    -0.22
    sten
    -0.20
    _STRIP
    -0.19
    åľĪåŃIJ
    -0.19
    kok
    -0.19
    kas
    -0.18
    -strip
    -0.18
     attempted
    -0.18
    é¾Ļ
    -0.18
    _attempt
    -0.18
    POSITIVE LOGITS
    åħģ许
    0.31
     allows
    0.27
    allows
    0.27
     позволÑı
    0.26
     позволÑıеÑĤ
    0.25
     allowing
    0.24
     allow
    0.24
    åħģ
    0.23
    è¶³å¤Ł
    0.23
    Allows
    0.22
    Activations Density 0.194%

    No Known Activations