© 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. 11207
    Prev
    Next
    INDEX
    Explanations

    eligible for criteria or trials

    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
    aceous
    -0.22
    iller
    -0.19
    -east
    -0.18
    ä¸įç»ıæĦı
    -0.18
    sexual
    -0.17
    aceut
    -0.16
    +len
    -0.16
    æĦıå¢ĥ
    -0.16
    aday
    -0.15
    .setInt
    -0.15
    POSITIVE LOGITS
    ged
    0.27
    ities
    0.23
    keiten
    0.19
    ìĤ¬íķŃ
    0.19
    iate
    0.18
    itas
    0.17
    å¦Ħ
    0.17
    idad
    0.17
    keit
    0.17
    èģª
    0.17
    Activations Density 0.005%

    No Known Activations