© 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. 14866
    Prev
    Next
    INDEX
    Explanations

    Red Hat, Red Sox, Red Wings

    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
    累累
    -0.20
    ensitive
    -0.19
     nghiá»ĩm
    -0.19
    soever
    -0.18
    s
    -0.18
    ained
    -0.17
    reading
    -0.16
    sdk
    -0.16
    /if
    -0.16
    owns
    -0.16
    POSITIVE LOGITS
    er
    0.37
    o
    0.24
    h
    0.23
    erator
    0.23
    ÑģÑĮ
    0.22
    iator
    0.21
    erate
    0.21
    endum
    0.20
    ا
    0.20
    oil
    0.20
    Activations Density 0.010%

    No Known Activations