© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15069
    Prev
    Next
    INDEX
    Explanations

    restart, reboot, reconnect, reset

    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
     Deutsch
    -0.19
    ires
    -0.19
    ób
    -0.19
    .pen
    -0.19
    kte
    -0.19
     Ford
    -0.19
     Grimm
    -0.19
    kop
    -0.18
    ghi
    -0.18
    uko
    -0.18
    POSITIVE LOGITS
    åĩłæ¬¡
    0.27
     reset
    0.24
    ä¸Ģ次
    0.23
    å¤ļ次
    0.23
     fresh
    0.22
    ãĤ
    0.21
    ä¸ī次
    0.21
    èĢģåĮĸ
    0.21
    ç©Ħ
    0.21
    æģ¢å¤įæŃ£å¸¸
    0.20
    Activations Density 0.092%

    No Known Activations