© 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. 13867
    Prev
    Next
    INDEX
    Explanations

    byte encoding schemes

    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
    FilterWhere
    -0.22
    Hon
    -0.21
    .mit
    -0.21
    	RTLR
    -0.21
    istol
    -0.21
    acre
    -0.20
    |RF
    -0.20
     Liberty
    -0.20
    olib
    -0.20
    eree
    -0.20
    POSITIVE LOGITS
     bytes
    0.31
    第ä¸Ģä½į
    0.30
     byte
    0.30
     encoded
    0.26
     bits
    0.25
    ç´§è·Ł
    0.25
    bits
    0.25
    两ä½į
    0.25
    Bytes
    0.25
     bit
    0.25
    Activations Density 0.383%

    No Known Activations