© 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. 11364
    Prev
    Next
    INDEX
    Explanations

    4 followed by units or counts

    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
    ution
    -0.20
    iger
    -0.19
    ching
    -0.18
    cliffe
    -0.18
    uch
    -0.17
    occo
    -0.17
    izable
    -0.16
    åĪĨæĺİ
    -0.16
    çļ¿
    -0.15
    enal
    -0.15
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.20
    eldo
    0.18
    OrNull
    0.17
     vá»±c
    0.17
    ReturnValue
    0.17
    mars
    0.17
    å°ıäºĭ
    0.16
    loo
    0.16
    หมาย
    0.16
    ç¼Ń
    0.16
    Activations Density 0.053%

    No Known Activations