© 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. 12107
    Prev
    Next
    INDEX
    Explanations

    casual

    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
    æľīåħ³éĥ¨éŨ
    -0.20
    aceous
    -0.19
    soever
    -0.18
    endum
    -0.17
    joy
    -0.17
    /her
    -0.16
    eming
    -0.16
     Runnable
    -0.16
    eder
    -0.15
    究竣
    -0.15
    POSITIVE LOGITS
    ties
    0.26
    itas
    0.25
    ly
    0.22
    -minded
    0.21
    ware
    0.21
    mente
    0.20
    cade
    0.20
     minded
    0.19
    ities
    0.19
    ruc
    0.18
    Activations Density 0.008%

    No Known Activations