© 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. 14871
    Prev
    Next
    INDEX
    Explanations

    Register documents

    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
    对åħ¶çľŁå®ŀ
    -0.23
    家ä¼Ļ
    -0.20
    æĿŀ
    -0.19
    rog
    -0.19
    é¢Ĩè·ij
    -0.19
    éĥĬ
    -0.19
    .Profile
    -0.19
    image
    -0.18
    hero
    -0.18
    娣
    -0.18
    POSITIVE LOGITS
    sonian
    0.24
    çī¹æ®ĬæĥħåĨµ
    0.22
    æ©ŁéĹľ
    0.21
    æŃ£æĸĩ
    0.21
    jem
    0.21
    纮
    0.20
    æ¦Ĥè¿°
    0.19
    åŁºæľ¬åİŁåĪĻ
    0.19
    åħ·ä½ĵæĥħåĨµ
    0.19
    sWith
    0.19
    Activations Density 0.002%

    No Known Activations