© 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. 13094
    Prev
    Next
    INDEX
    Explanations

    cash dispenser, ATM, withdrawals

    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
    鸳
    -0.21
    linger
    -0.20
    onia
    -0.20
    å°ļ
    -0.19
    è¤ĵ
    -0.19
    èħ»
    -0.19
    ç¿İ
    -0.18
    /licenses
    -0.18
    ght
    -0.17
    裱
    -0.17
    POSITIVE LOGITS
    éĵ¶è¡Įåį¡
    0.30
    éĵ¶è¡Į
    0.27
    é¢ijé¢ij
    0.26
    éĩijèŀįç§ijæĬĢ
    0.25
    omat
    0.25
    éĩijèŀįæľºæŀĦ
    0.25
    éĵ¶è¡Įä¸ļ
    0.25
     bank
    0.24
     ATM
    0.24
    èĩªåĬ©
    0.24
    Activations Density 0.010%

    No Known Activations