© 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. 11645
    Prev
    Next
    INDEX
    Explanations

    available, have, no

    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
     Keeps
    -0.22
    IDO
    -0.20
     lashes
    -0.19
    lix
    -0.18
    çīĿ
    -0.18
    LING
    -0.18
    bomb
    -0.18
     baff
    -0.18
    idd
    -0.18
    _keep
    -0.17
    POSITIVE LOGITS
    åı¯çĶ¨
    0.29
     available
    0.26
    available
    0.24
    æ¬łç¼º
    0.21
    ataire
    0.21
     Available
    0.21
    Available
    0.21
    åĮ®ä¹ı
    0.20
    ä¸į足
    0.20
    家ä¸Ń
    0.20
    Activations Density 0.080%

    No Known Activations