© 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. 10896
    Prev
    Next
    INDEX
    Explanations

    sex or interview context

    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
    å¸ĺ
    -0.22
     cheerful
    -0.21
    çij°
    -0.21
    涧
    -0.20
     whisk
    -0.20
     probabil
    -0.20
     cheer
    -0.20
    Optional
    -0.20
    èĦĬ
    -0.20
     nast
    -0.20
    POSITIVE LOGITS
    gMaps
    0.31
    numerusform
    0.29
    ÑĢеги
    0.29
    Cumhur
    0.27
    .opensource
    0.27
    STANCE
    0.26
    PropertyParams
    0.26
     nuru
    0.26
    >NN
    0.26
    thèse
    0.25
    Activations Density 0.119%

    No Known Activations