© 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. 15759
    Prev
    Next
    INDEX
    Explanations

    objects in outdoor environments

    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
    ç¦
    -0.19
    好好
    -0.19
     ÙĦÙĥÙĦ
    -0.18
    ="__
    -0.18
    åħ¶éĹ´
    -0.18
    èı¡
    -0.18
     ÑģамÑĭÑħ
    -0.18
    åħĥ
    -0.17
    çĸ¡
    -0.17
    大çģ«
    -0.17
    POSITIVE LOGITS
    çªĦ
    0.21
    è¿ijè·Ŀ离
    0.19
     near
    0.19
    追éĢIJ
    0.18
    åĿİ
    0.18
    çĭŃçªĦ
    0.18
    (QIcon
    0.18
    rips
    0.18
    atype
    0.18
    idis
    0.17
    Activations Density 0.049%

    No Known Activations