© 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. 10862
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical suffixes

    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
    arsity
    -0.20
     dara
    -0.18
    /watch
    -0.18
     compromise
    -0.18
    ç¢ī
    -0.18
    FormControl
    -0.18
    ï¸
    -0.18
    ModelError
    -0.17
    _ctl
    -0.17
     compromised
    -0.17
    POSITIVE LOGITS
    çĸĹç¨ĭ
    0.20
    blind
    0.20
    averse
    0.20
    å±¥
    0.20
    çĹ´è¿·
    0.18
     Alam
    0.18
    èį¯åĵģ
    0.18
    æ§İ
    0.18
    getTable
    0.18
    liness
    0.18
    Activations Density 0.069%

    No Known Activations