© 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. 12034
    Prev
    Next
    INDEX
    Explanations

    thread and strand related terms

    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
    iones
    -0.18
    omat
    -0.17
    plier
    -0.17
    uable
    -0.15
    wards
    -0.15
    å®ŀæķĪ
    -0.15
    äºĽä»Ģä¹Ī
    -0.15
    lico
    -0.15
    imum
    -0.15
    adium
    -0.15
    POSITIVE LOGITS
    line
    0.24
    less
    0.23
    .currentThread
    0.22
    lines
    0.19
    olf
    0.19
    bare
    0.18
     пиÑĤаниÑı
    0.18
    lined
    0.17
    le
    0.17
    emann
    0.17
    Activations Density 0.031%

    No Known Activations