© 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. 12243
    Prev
    Next
    INDEX
    Explanations

    presenting information or ideas

    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
    æ°ijå¿ĥ
    -0.18
    æ·±å¤Ħ
    -0.17
    OrCreate
    -0.17
    onna
    -0.17
    -0.17
    ths
    -0.16
    rint
    -0.16
    pedia
    -0.16
    akov
    -0.16
    yards
    -0.16
    POSITIVE LOGITS
     Ñģобой
    0.30
    ational
    0.21
    -day
    0.21
    à¹ģà¸Ļะ
    0.19
    ç»Ļ大家
    0.18
    ural
    0.18
    ål
    0.17
    ion
    0.17
    imiento
    0.17
    ively
    0.16
    Activations Density 0.115%

    No Known Activations