© 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. 12993
    Prev
    Next
    INDEX
    Explanations

    Reuters or Bloomberg news reports

    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
    _MEMBERS
    -0.20
    æ¤Ĵ
    -0.20
     repe
    -0.20
    /questions
    -0.18
    лаÑģÑĤ
    -0.18
     Keywords
    -0.18
    aded
    -0.17
    \Traits
    -0.17
    éĢłæŀĹ
    -0.17
    ì§ĢìĽIJ
    -0.17
    POSITIVE LOGITS
    oi
    0.21
    andle
    0.20
    awe
    0.20
    çįł
    0.18
    ÑģÑĥд
    0.18
     Dude
    0.18
    pathname
    0.18
    ढ
    0.18
    expected
    0.18
    .expected
    0.18
    Activations Density 0.001%

    No Known Activations