© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15197
    Prev
    Next
    INDEX
    Explanations

    sedan

    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
    sell
    -0.21
    sheets
    -0.19
    sheet
    -0.19
    school
    -0.18
    ome
    -0.17
    ses
    -0.17
    sk
    -0.17
    session
    -0.17
    lic
    -0.17
    sing
    -0.17
    POSITIVE LOGITS
    rd
    0.18
     THROW
    0.18
    çĦ¦
    0.17
    estre
    0.17
    GING
    0.17
     NotImplemented
    0.17
    rf
    0.17
     gắng
    0.17
    rück
    0.17
     ünl
    0.16
    Activations Density 0.010%

    No Known Activations