© 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. 15543
    Prev
    Next
    INDEX
    Explanations

    departments or fields of study

    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
     a
    -0.25
     kind
    -0.23
    “
    -0.23
     “
    -0.23
     up
    -0.23
    ↵
    -0.23
     on
    -0.22
     sole
    -0.22
    ,
    -0.22
     part
    -0.22
    POSITIVE LOGITS
    _ComCallableWrapper
    0.23
    _:*
    0.22
    ernetes
    0.22
    ¡´
    0.21
     shemale
    0.20
    ÓĽ
    0.20
    iéndo
    0.20
     milfs
    0.20
     sourceMapping
    0.20
     nuru
    0.20
    Activations Density 0.183%

    No Known Activations