© 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. 11959
    Prev
    Next
    INDEX
    Explanations

    oxidation

    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
    ismatic
    -0.21
    åĴĮåľ°åĮº
    -0.18
    ocal
    -0.17
    iban
    -0.16
    ald
    -0.15
    ç¾²
    -0.15
    èĿĩ
    -0.15
    ÑĩаÑģÑĤ
    -0.15
    quite
    -0.15
    ifest
    -0.15
    POSITIVE LOGITS
    0.19
    plorer
    0.18
    cul
    0.17
    çĦĻ
    0.17
    allis
    0.17
    ations
    0.16
    iation
    0.16
    vido
    0.16
    ores
    0.16
    tures
    0.16
    Activations Density 0.058%

    No Known Activations