© 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. 11138
    Prev
    Next
    INDEX
    Explanations

    peel off

    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
    sWith
    -0.20
     sourceMapping
    -0.17
    ODO
    -0.17
    itious
    -0.16
    zd
    -0.16
    ional
    -0.16
    eam
    -0.16
    /people
    -0.16
    iming
    -0.15
    unker
    -0.15
    POSITIVE LOGITS
    ings
    0.21
     khá»ıi
    0.19
    out
    0.18
    ABLE
    0.18
     respective
    0.17
    æİī
    0.17
    ables
    0.17
    LES
    0.17
    eso
    0.17
    outs
    0.16
    Activations Density 0.006%

    No Known Activations