© 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. 12926
    Prev
    Next
    INDEX
    Explanations

    paste

    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
    nty
    -0.23
    arton
    -0.22
    xFD
    -0.22
    antor
    -0.18
    theless
    -0.18
    Ñģен
    -0.18
    swith
    -0.17
    rieg
    -0.17
    GuidId
    -0.17
    æīī
    -0.17
    POSITIVE LOGITS
     into
    0.26
    Into
    0.24
    into
    0.23
    åİŁæĸĩ
    0.22
    åĩºæĿ¥çļĦ
    0.22
    frag
    0.20
    è¿Ľåİ»
    0.20
    aneously
    0.19
    åħ¬åħ±åľºæīĢ
    0.19
     onto
    0.19
    Activations Density 0.012%

    No Known Activations