© 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. 15386
    Prev
    Next
    INDEX
    Explanations

    printing and art terms

    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
    榫
    -0.22
    çķħéĢļ
    -0.21
     veto
    -0.20
    Clip
    -0.18
    _trees
    -0.18
    oins
    -0.18
    unce
    -0.18
    .habbo
    -0.18
    egov
    -0.18
    rait
    -0.18
    POSITIVE LOGITS
    Cel
    0.21
    åħµé©¬
    0.20
     verg
    0.19
    Dup
    0.19
     Cel
    0.18
    åĬŁå¾·
    0.18
    erne
    0.18
    _DOM
    0.18
    -repeat
    0.18
    tet
    0.18
    Activations Density 0.001%

    No Known Activations