© 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. 14412
    Prev
    Next
    INDEX
    Explanations

    paper towels

    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
    dot
    -0.22
    æł¡åıĭ
    -0.21
    è²´
    -0.20
    è´µ
    -0.20
    ITLE
    -0.20
    è¹Ī
    -0.19
    æįIJèµł
    -0.19
    Dot
    -0.19
    èłķ
    -0.19
    é¡·
    -0.18
    POSITIVE LOGITS
    大éĻĨ
    0.19
    gé
    0.19
    é¾ĻéŨ
    0.19
    ceÄŁi
    0.19
     editorial
    0.18
    åĸľæ¬¢åIJĥ
    0.18
    å°½éĩı
    0.18
    è°¦
    0.18
    .pref
    0.18
     дополниÑĤелÑĮно
    0.18
    Activations Density 0.001%

    No Known Activations