© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10590
    Prev
    Next
    INDEX
    Explanations

    plot labels and axes

    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
    FilterWhere
    -0.29
    PropertyParams
    -0.29
    _Parms
    -0.24
     newcom
    -0.23
    gMaps
    -0.22
    çĩİ
    -0.22
    .Maximum
    -0.21
    CallCheck
    -0.21
    ⧫
    -0.20
    eya
    -0.20
    POSITIVE LOGITS
     ordin
    0.27
    纵
    0.25
    label
    0.25
     labels
    0.23
     ord
    0.23
     label
    0.22
    Name
    0.22
    ä¸Ĭæľī
    0.21
    éĻĪåĪĹ
    0.21
    col
    0.21
    Activations Density 0.342%

    No Known Activations