© 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. 11023
    Prev
    Next
    INDEX
    Explanations

    again words

    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»Ģä¹Īéĥ½ä¸į
    -0.19
    vak
    -0.19
    åįģåĩłå¹´
    -0.18
    Ử
    -0.18
    esian
    -0.18
    èĤ©èĨĢ
    -0.18
    常年
    -0.17
    \\\\
    -0.17
    åĽłæѤ
    -0.17
    è¸Į
    -0.17
    POSITIVE LOGITS
     again
    0.54
    åĨį次
    0.52
    åĨįä¸Ģ次
    0.50
    again
    0.48
    åıĪä¸Ģ次
    0.47
    åĨį度
    0.44
    Again
    0.43
     Again
    0.40
     Ñģнова
    0.34
     novamente
    0.34
    Activations Density 0.110%

    No Known Activations