© 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. 15631
    Prev
    Next
    INDEX
    Explanations

    vertical continuations

    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
    atical
    -0.17
    fully
    -0.16
    hips
    -0.16
    licit
    -0.16
    place
    -0.15
    lesh
    -0.15
    械
    -0.15
    åģľçĶµ
    -0.15
    venture
    -0.15
    acker
    -0.15
    POSITIVE LOGITS
    ity
    0.30
    izable
    0.22
    -minded
    0.20
    -lived
    0.20
    ally
    0.20
    ities
    0.19
    uhn
    0.18
    cut
    0.18
    ITY
    0.18
    zig
    0.18
    Activations Density 0.030%

    No Known Activations