© 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. 10745
    Prev
    Next
    INDEX
    Explanations

    tape, taping, tape backups, tape-automatic

    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
    æµij
    -0.20
     Nach
    -0.19
    IG
    -0.19
    bes
    -0.19
    ror
    -0.18
    èĸ°
    -0.18
    ACT
    -0.18
    CR
    -0.17
     Brew
    -0.17
    å¿ĥå¢ĥ
    -0.17
    POSITIVE LOGITS
    IDEO
    0.23
    OLER
    0.21
    iah
    0.20
    stry
    0.20
    quine
    0.19
    ince
    0.19
    æĿ¡
    0.19
    _tensors
    0.19
    omatic
    0.18
    èĥ½æĬĬ
    0.18
    Activations Density 0.004%

    No Known Activations