© 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. 14613
    Prev
    Next
    INDEX
    Explanations

    real estate, real-time, Real Madrid, Realtek

    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
    yard
    -0.21
    esy
    -0.18
    elsen
    -0.17
    esis
    -0.17
    eenth
    -0.17
    ë°Ľ
    -0.17
    esse
    -0.16
    иÑĪ
    -0.16
    kus
    -0.16
    een
    -0.15
    POSITIVE LOGITS
    istically
    0.28
    ities
    0.23
    mente
    0.23
    ationship
    0.20
    istic
    0.20
    åIJĦæł·
    0.20
    ignment
    0.19
    pollo
    0.19
    izable
    0.18
    mention
    0.18
    Activations Density 0.034%

    No Known Activations