© 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. 14800
    Prev
    Next
    INDEX
    Explanations

    brief introduction or discussion

    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¤§åĽ½
    -0.19
    wards
    -0.18
    thèque
    -0.17
    主è¦ģåİŁåĽł
    -0.17
    aved
    -0.16
    usher
    -0.16
    è¦ģæĬĬ
    -0.16
    APE
    -0.16
    usi
    -0.15
    峦
    -0.15
    POSITIVE LOGITS
    ness
    0.27
    ly
    0.25
    emente
    0.23
    ement
    0.20
    zeitig
    0.20
    ëĭĿ
    0.20
    est
    0.19
    LY
    0.19
    ify
    0.19
    /small
    0.19
    Activations Density 0.013%

    No Known Activations