© 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. 12383
    Prev
    Next
    INDEX
    Explanations

    `import` and `.ComponentModel`

    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
    vir
    -0.20
    éĿ¢åĮħ
    -0.19
    ÑĤика
    -0.19
    åı£è¢ĭ
    -0.19
    hood
    -0.18
    ãģ¯ãģļ
    -0.18
     ach
    -0.18
    XC
    -0.18
    chant
    -0.18
    åľ¬
    -0.17
    POSITIVE LOGITS
    çŁ³æ²¹
    0.19
    çĤ·
    0.19
    uuid
    0.18
    éĽī
    0.18
    ä»ĸåıĪ
    0.18
    æ½ľèīĩ
    0.18
    OTOR
    0.18
     oil
    0.18
     Oil
    0.17
    èĢģèĻİ
    0.17
    Activations Density 0.231%

    No Known Activations