© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10538
    Prev
    Next
    INDEX
    Explanations

    fairness and use

    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
    Negative Logits
    pty
    -0.20
    MAND
    -0.20
    妹
    -0.19
    aching
    -0.18
    chn
    -0.17
    TOR
    -0.17
    isha
    -0.17
    anner
    -0.17
    ives
    -0.17
    éķ¿çŁŃ
    -0.17
    POSITIVE LOGITS
    ness
    0.32
    theless
    0.22
    nya
    0.22
    son
    0.20
    оÑĢÑĤ
    0.19
    ly
    0.18
    -conscious
    0.18
    ÑĤÑĢа
    0.18
    rides
    0.18
    çŨ
    0.18
    Activations Density 0.004%

    No Known Activations