© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15317
    Prev
    Next
    INDEX
    Explanations

    game score outcome

    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
    â¼Ĵ
    -0.20
    uces
    -0.19
    avic
    -0.19
    commons
    -0.18
    _rq
    -0.18
    autocomplete
    -0.17
     nghá»ģ
    -0.17
    ä½ľèĢħæľ¬äºº
    -0.17
     lắm
    -0.17
    _roles
    -0.17
    POSITIVE LOGITS
    /-
    0.20
    ohana
    0.19
     marg
    0.19
    tring
    0.19
     Marg
    0.19
    æŁĦ
    0.18
    /+
    0.18
    ç²²
    0.18
     Barb
    0.18
    汶
    0.17
    Activations Density 0.005%

    No Known Activations