© 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. 15680
    Prev
    Next
    INDEX
    Explanations

    idiopathic or today

    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
    liest
    -0.21
    çģµæķı
    -0.19
    protobuf
    -0.18
    orial
    -0.18
    ãĥIJãĥ©
    -0.17
    ponder
    -0.17
    æĬijéĥģ
    -0.17
    æĭĺ
    -0.17
    uch
    -0.17
     fre
    -0.16
    POSITIVE LOGITS
    åĴĮåľ°åĮº
    0.19
    gee
    0.18
    å¤ĸå¥Ĺ
    0.18
     bá»ģ
    0.18
    rica
    0.18
     Hodg
    0.17
     fizz
    0.17
     ÑĢож
    0.17
     Hoy
    0.16
    èĭį
    0.16
    Activations Density 0.004%

    No Known Activations