© 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. 13552
    Prev
    Next
    INDEX
    Explanations

    boom or doom

    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
    angelo
    -0.20
    è¡Į车
    -0.19
    -leaning
    -0.17
    à¹Į
    -0.17
    ãģĦãĤĭ
    -0.16
    ´
    -0.16
    TING
    -0.16
    -speaking
    -0.16
    -football
    -0.15
    formats
    -0.15
    POSITIVE LOGITS
    ingly
    0.29
    lets
    0.20
    strap
    0.19
    pty
    0.18
    aroo
    0.17
    ify
    0.17
    frog
    0.17
    rise
    0.16
    iest
    0.16
    ish
    0.16
    Activations Density 0.005%

    No Known Activations