© 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. 11804
    Prev
    Next
    INDEX
    Explanations

    cook

    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
    éĩįéĩį
    -0.18
    	TokenName
    -0.17
    IONS
    -0.17
    _ATTRIB
    -0.17
    immer
    -0.17
    eof
    -0.17
    ials
    -0.17
    pir
    -0.16
    ราà¸Ĭ
    -0.16
    auce
    -0.16
    POSITIVE LOGITS
    sey
    0.23
    inary
    0.22
    liness
    0.21
    ģ
    0.19
    ery
    0.19
    son
    0.18
    etable
    0.18
    ings
    0.18
    ly
    0.17
    uet
    0.17
    Activations Density 0.023%

    No Known Activations