© 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. 10746
    Prev
    Next
    INDEX
    Explanations

    when followed by I

    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
    ä¾Ľæ±Ĥ
    -0.19
    èĽĭ
    -0.18
    urf
    -0.18
    pine
    -0.17
    ãģº
    -0.17
    xba
    -0.17
    å²Ķ
    -0.17
    ãģĻãģİãĤĭ
    -0.17
    _pv
    -0.17
    )application
    -0.17
    POSITIVE LOGITS
    以æѤ
    0.20
     Dove
    0.19
     Arms
    0.19
    MOST
    0.19
    INGS
    0.19
    è¿Ļå¥Ĺ
    0.19
    缴èĩ³
    0.18
    åŀĵ
    0.18
     arms
    0.18
    ran
    0.17
    Activations Density 0.263%

    No Known Activations