© 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. 15041
    Prev
    Next
    INDEX
    Explanations

    query syntax or usage

    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
    çĦ¶æĺ¯
    -0.20
    uation
    -0.17
    uzzi
    -0.17
    uate
    -0.16
    illery
    -0.16
    ning
    -0.16
    aging
    -0.16
    èĨº
    -0.16
    ène
    -0.16
    otech
    -0.15
    POSITIVE LOGITS
    able
    0.20
    lew
    0.19
    eing
    0.18
    ELLOW
    0.17
    dsl
    0.17
    naire
    0.16
    ndo
    0.16
    esz
    0.15
    des
    0.15
    ©
    0.15
    Activations Density 0.058%

    No Known Activations