© 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. 12135
    Prev
    Next
    INDEX
    Explanations

    use or may use cookies

    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
     necessarily
    -0.19
     cogn
    -0.19
    fer
    -0.18
    å¾ĹåĪ°æľīæķĪ
    -0.18
    åºĶæľīçļĦ
    -0.18
    çIJĨæĥ³çļĦ
    -0.18
     annihil
    -0.18
    ancy
    -0.17
    ä¸ĭåįķ
    -0.17
    被æī§è¡Į
    -0.17
    POSITIVE LOGITS
    ä¸įå®ļ
    0.22
    ticks
    0.20
    _GF
    0.19
    aits
    0.19
    OutOf
    0.19
    åĿļå®ļä¸į
    0.18
    _Surface
    0.18
    éĽķå¡ij
    0.18
    olds
    0.18
    å®ļæľŁ
    0.18
    Activations Density 0.032%

    No Known Activations