© 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. 10690
    Prev
    Next
    INDEX
    Explanations

    share

    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
    ses
    -0.23
    onet
    -0.22
    oney
    -0.21
    sed
    -0.20
     Lives
    -0.19
     pur
    -0.19
    elts
    -0.19
    æį¶
    -0.19
    atically
    -0.19
    atten
    -0.18
    POSITIVE LOGITS
    åĪĨ享
    0.20
    åħ±äº«
    0.20
    share
    0.20
    _flip
    0.19
     Sachs
    0.19
    å®´ä¼ļ
    0.18
    åıijè´¢
    0.18
    .share
    0.18
    éĺħåİĨ
    0.18
     оÑĢган
    0.17
    Activations Density 0.024%

    No Known Activations