© 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. 16085
    Prev
    Next
    INDEX
    Explanations

    image processing concepts

    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
    _ALARM
    -0.24
    ALAR
    -0.23
    ABB
    -0.22
    inox
    -0.21
    istol
    -0.21
    _alarm
    -0.20
    CloseOperation
    -0.20
    :convert
    -0.20
    chu
    -0.20
    .converter
    -0.20
    POSITIVE LOGITS
    ç»Ĩèħ»
    0.26
     edge
    0.26
    éĶIJ
    0.25
    åĢį
    0.25
    edges
    0.24
     edges
    0.24
    edge
    0.23
     grid
    0.23
    åĥıç´ł
    0.23
    åĪĨ辨çİĩ
    0.23
    Activations Density 0.076%

    No Known Activations