© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15165
    Prev
    Next
    INDEX
    Explanations

    PlayStation gaming consoles and services

    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
    s
    -0.19
    ially
    -0.18
    stan
    -0.18
    suit
    -0.18
    cit
    -0.18
    èĬ¹
    -0.17
    tc
    -0.17
    square
    -0.17
    涣
    -0.17
    ingly
    -0.17
    POSITIVE LOGITS
    upported
    0.19
    TM
    0.18
    è¿Ļ个åIJįåŃĹ
    0.18
    baugh
    0.18
    ®
    0.17
    ÃĸZ
    0.17
    neau
    0.17
    orgia
    0.16
    örü
    0.16
    ĥģ
    0.16
    Activations Density 0.004%

    No Known Activations