© 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. 16000
    Prev
    Next
    INDEX
    Explanations

    program copyright

    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
    	iNdEx
    -0.25
    VML
    -0.22
     Everett
    -0.22
     seiz
    -0.21
     thinly
    -0.21
    inges
    -0.20
    棣
    -0.20
    à¸Ĭวà¸Ļ
    -0.20
     podcasts
    -0.20
     provoc
    -0.20
    POSITIVE LOGITS
     arsch
    0.33
     münchen
    0.33
     follando
    0.32
     salopes
    0.32
     geschichten
    0.31
     erotisk
    0.31
     männer
    0.31
     tjejer
    0.31
     köln
    0.31
     наÑĢко
    0.31
    Activations Density 0.200%

    No Known Activations