© 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. 13597
    Prev
    Next
    INDEX
    Explanations

    save something

    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
    ship
    -0.22
    ships
    -0.21
    ãģĦãģ¾ãģĻ
    -0.21
    ients
    -0.21
    éĩįéĩį
    -0.20
    naire
    -0.20
    sWith
    -0.20
    atics
    -0.20
     Ñģобой
    -0.19
    ses
    -0.19
    POSITIVE LOGITS
    OrUpdate
    0.22
    Ùĭ
    0.19
    ableObject
    0.18
    oola
    0.16
    олÑĮ
    0.16
    ðŁı»
    0.16
    าว
    0.16
     Bought
    0.16
    LER
    0.16
    jee
    0.16
    Activations Density 0.014%

    No Known Activations