© 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. 15787
    Prev
    Next
    INDEX
    Explanations

    recommendations and advice

    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
    _HISTORY
    -0.21
    èĬĿ
    -0.20
    History
    -0.20
    >Show
    -0.19
    Phoenix
    -0.19
    .closed
    -0.19
    _proof
    -0.19
    åĢĴå¡Į
    -0.18
    velope
    -0.18
    history
    -0.18
    POSITIVE LOGITS
    建议
    0.49
     advice
    0.49
     advise
    0.47
    æݨèįIJ
    0.46
     advised
    0.43
     advises
    0.43
     recommendations
    0.40
    建èŃ°
    0.38
     recommendation
    0.38
     recomend
    0.37
    Activations Density 0.239%

    No Known Activations