© 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. 15940
    Prev
    Next
    INDEX
    Explanations

    Greg followed by name

    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
    gence
    -0.18
    ä¸įäºĨ
    -0.17
    çĻ£
    -0.17
    tte
    -0.17
    wyn
    -0.15
    mega
    -0.15
    -hearted
    -0.15
    ร
    -0.15
    ered
    -0.15
    è¯ķåīĤ
    -0.15
    POSITIVE LOGITS
    ification
    0.19
    ingly
    0.19
    inct
    0.18
    ening
    0.17
    ally
    0.17
    icle
    0.17
    bole
    0.17
    ual
    0.16
    opia
    0.16
    abyte
    0.16
    Activations Density 0.048%

    No Known Activations