© 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. 12387
    Prev
    Next
    INDEX
    Explanations

    free software license

    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
    åħ¬ç¤¾
    -0.19
    SHIP
    -0.19
     ims
    -0.18
    fcc
    -0.17
    庶
    -0.17
    /inc
    -0.17
    éªĿ
    -0.17
    -gradient
    -0.17
    彤
    -0.17
     Eag
    -0.17
    POSITIVE LOGITS
    æ½ĩ
    0.21
    arak
    0.18
    åı©
    0.18
    ASM
    0.18
    ascar
    0.18
    @a
    0.17
    ãģ¾ãģ§
    0.17
     Clem
    0.17
     TAR
    0.17
    æķ²
    0.17
    Activations Density 0.015%

    No Known Activations