© 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. 13779
    Prev
    Next
    INDEX
    Explanations

    blog post writing

    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
     ÐIJлекÑģан
    -0.36
     Geile
    -0.33
     наÑĢко
    -0.33
     Erotische
    -0.32
     mükem
    -0.31
     пÑĢиÑıÑĤн
    -0.31
    ãĤŃãĥ£ãĥ³ãĥļ
    -0.31
     tjejer
    -0.31
    еÑģÑĤеÑģÑĤвенн
    -0.30
     моÑīн
    -0.30
    POSITIVE LOGITS
    æĸĩåĮĸéģĹ产
    0.26
    è®Ģ
    0.26
    æĸĩåĮĸ交æµģ
    0.26
     centuries
    0.25
    Western
    0.25
    西æĸ¹
    0.24
    æĸĩçī©
    0.24
    åİĨåı²
    0.24
    èĩ´æķ¬
    0.24
    èµıæŀIJ
    0.24
    Activations Density 0.390%

    No Known Activations