© 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. 12408
    Prev
    Next
    INDEX
    Explanations

    quantifiers and intensifiers

    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
    zell
    -0.21
    迳
    -0.21
     todav
    -0.20
    æĬ¢åħĪ
    -0.19
     sobie
    -0.19
    å¾ij
    -0.19
    _modified
    -0.17
     hoop
    -0.17
    Msp
    -0.17
    APTER
    -0.17
    POSITIVE LOGITS
     ones
    0.29
    tail
    0.22
     vice
    0.22
     Ones
    0.20
     tail
    0.20
    frm
    0.19
    vice
    0.19
    åĵī
    0.18
    ạ
    0.18
    å°¾
    0.18
    Activations Density 0.121%

    No Known Activations