© 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. 12100
    Prev
    Next
    INDEX
    Explanations

    call to action

    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
    Employ
    -0.20
    éĤ£æł·çļĦ
    -0.20
    OMET
    -0.19
    ynes
    -0.19
    itra
    -0.19
    èĴĻ
    -0.18
    cri
    -0.18
    omet
    -0.18
     Philipp
    -0.18
    klä
    -0.18
    POSITIVE LOGITS
    åħ·ä½ĵåĨħ容
    0.23
    æľ¬æ¬¡
    0.23
    åħ·ä½ĵæĥħåĨµ
    0.23
    ä¸ĭéĿ¢æĪij们
    0.23
    çĭ¬å®¶
    0.23
    éĻIJè´Ń
    0.22
    详è§ģ
    0.22
    è°į
    0.21
    å¦Ĥä¸ĭ
    0.20
    çļĦåħ·ä½ĵ
    0.20
    Activations Density 0.018%

    No Known Activations