© 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. 15855
    Prev
    Next
    INDEX
    Explanations

    distribution of terms

    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
    ì§ľ
    -0.18
    ctype
    -0.18
    æ»ĵ
    -0.17
    åģļçļĦäºĭ
    -0.16
    ../
    -0.15
    bones
    -0.15
    eron
    -0.15
    _INITIALIZ
    -0.15
    -quarters
    -0.14
    ulous
    -0.14
    POSITIVE LOGITS
    ally
    0.28
    ively
    0.26
    ALLY
    0.20
    ãģĹãģ¾ãģĨ
    0.17
    lew
    0.17
    reak
    0.16
    ational
    0.16
    leh
    0.16
    inct
    0.16
    KeyCode
    0.16
    Activations Density 0.075%

    No Known Activations