© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15171
    Prev
    Next
    INDEX
    Explanations

    bl followed by anton or oun

    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
    ally
    -0.22
    orem
    -0.18
    /legal
    -0.17
    sty
    -0.16
    ality
    -0.16
    ész
    -0.16
    ãĥ£
    -0.15
    æĢ»çIJĨ
    -0.15
    ainty
    -0.15
    éļį
    -0.15
    POSITIVE LOGITS
    itt
    0.19
    ubber
    0.18
    hum
    0.16
    paren
    0.15
    aney
    0.15
    hawk
    0.15
    otec
    0.15
    !--
    0.14
    buster
    0.14
    izzy
    0.14
    Activations Density 0.038%

    No Known Activations