© 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. 16501
    Prev
    Next
    INDEX
    Explanations

    computer components and operations

    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
    PropertyParams
    -0.40
    CallableWrapper
    -0.32
    FilterWhere
    -0.31
    ValueHandling
    -0.30
    .Disclaimer
    -0.29
    <translation
    -0.29
     iNdEx
    -0.29
    ImageRelation
    -0.29
    GuidId
    -0.29
    ÑĩÑĢежден
    -0.29
    POSITIVE LOGITS
    常说
    0.31
    被称为
    0.29
    æĹłæķ°
    0.27
    çĶ»çĶ»
    0.26
    èĮĦåŃIJ
    0.25
    èµĸ以
    0.25
     okreÅĽ
    0.25
    ä¿Ĺ称
    0.25
    éĢļä¿Ĺ
    0.24
    称为
    0.24
    Activations Density 0.741%

    No Known Activations