© 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. 12944
    Prev
    Next
    INDEX
    Explanations

    class definitions or variable names

    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
    FilterWhere
    -0.25
    .drawer
    -0.22
    (Initialized
    -0.22
    ButtonTitles
    -0.21
    .RecyclerView
    -0.21
    _icall
    -0.21
    .visitMethod
    -0.21
    å±ī
    -0.19
    :UITableView
    -0.19
    wüns
    -0.19
    POSITIVE LOGITS
    ç±»
    0.28
    Holder
    0.27
    对象
    0.27
     namedtuple
    0.26
    Builder
    0.25
    Wrapper
    0.25
    ãĤ¯ãĥ©ãĤ¹
    0.24
     íģ´ëŀĺìĬ¤
    0.24
    Factory
    0.24
     пÑĢиÑıÑĤн
    0.24
    Activations Density 1.714%

    No Known Activations