© 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. 16106
    Prev
    Next
    INDEX
    Explanations

    cant or mand

    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
    ially
    -0.17
    é²ł
    -0.16
    tones
    -0.15
    鹧
    -0.15
    леÑĤ
    -0.15
    oodoo
    -0.15
    бил
    -0.15
    æīĭèħķ
    -0.15
    ìķ¼
    -0.15
    ungs
    -0.15
    POSITIVE LOGITS
    ations
    0.16
    achu
    0.15
    /w
    0.15
    å±ij
    0.15
    epad
    0.15
    ìį¨
    0.15
    Aus
    0.15
    or
    0.15
    owers
    0.14
    uvo
    0.14
    Activations Density 0.011%

    No Known Activations