© 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. 12252
    Prev
    Next
    INDEX
    Explanations

    Sam followed by last name

    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
     Ñģами
    -0.17
    edList
    -0.17
    orne
    -0.16
    æģ¤
    -0.16
    _POINTER
    -0.16
    isel
    -0.16
     внимание
    -0.15
    edm
    -0.15
    ONT
    -0.15
    ances
    -0.15
    POSITIVE LOGITS
    ware
    0.20
    常åĬ¡åī¯
    0.19
    -sized
    0.18
    uele
    0.17
    intosh
    0.17
    ä»
    0.16
    ways
    0.16
    ially
    0.16
    plings
    0.16
    们çļĦ
    0.15
    Activations Density 0.033%

    No Known Activations