© 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. 14138
    Prev
    Next
    INDEX
    Explanations

    âĢ² dimensions or measures

    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
    nya
    -0.20
    ness
    -0.19
    tha
    -0.18
    datum
    -0.17
    dek
    -0.17
    tru
    -0.16
    ãĥĥãĥī
    -0.16
    atics
    -0.15
    asm
    -0.15
    oid
    -0.15
    POSITIVE LOGITS
    èĩ¾
    0.18
    entifier
    0.17
    ive
    0.17
    ision
    0.17
    alysis
    0.17
    oser
    0.16
    entication
    0.16
    า
    0.16
    ity
    0.16
    orld
    0.15
    Activations Density 0.047%

    No Known Activations