© 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. 16921
    Prev
    Next
    INDEX
    Explanations

    relations between

    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
    å¨ĺ
    -0.18
    ernet
    -0.18
    arel
    -0.17
    oco
    -0.16
     Garrison
    -0.16
    allow
    -0.16
    encil
    -0.16
    lation
    -0.16
     allen
    -0.16
    ling
    -0.15
    POSITIVE LOGITS
    istic
    0.23
    ief
    0.19
    encing
    0.18
    iton
    0.16
    ately
    0.16
    è¾ĺ
    0.16
    ioned
    0.16
    ively
    0.16
    icut
    0.16
    ities
    0.15
    Activations Density 0.081%

    No Known Activations