© 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. 16546
    Prev
    Next
    INDEX
    Explanations

    dates after on

    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
     pneum
    -0.20
    Church
    -0.19
    .sd
    -0.19
    åħ¨çIJĥåĮĸ
    -0.18
    Authority
    -0.18
    åijµ
    -0.18
    ä¸ĭä¸ĢæŃ¥
    -0.18
    илоÑģÑĮ
    -0.17
    že
    -0.17
    å±ķæľĽ
    -0.17
    POSITIVE LOGITS
    ÑĦа
    0.20
    lotte
    0.20
    견
    0.19
    RESSION
    0.19
    è§ģåĪ°
    0.19
    èIJ½åľ°
    0.19
    çĶŁåij½åij¨æľŁ
    0.18
    æĢ§èĥ½
    0.18
    orsi
    0.17
    éĻį
    0.17
    Activations Density 0.001%

    No Known Activations