© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12312
    Prev
    Next
    INDEX
    Explanations

    determiners and titles

    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
     another
    -0.21
    ä¸ĢèĤ¡
    -0.18
    çľī
    -0.17
    åı¦ä¸Ģ
    -0.17
    éĹŃ
    -0.17
    udge
    -0.17
     дÑĢÑĥг
    -0.17
    another
    -0.17
    edi
    -0.17
    town
    -0.17
    POSITIVE LOGITS
    éĥ¨åĪĨ
    0.22
    éĥ¨åĪĨåĨħ容
    0.21
    åĽļ
    0.21
    lices
    0.20
    éĥ¨ä»½
    0.19
    IRON
    0.19
    å½»
    0.19
    asher
    0.18
    jour
    0.18
     Portions
    0.18
    Activations Density 0.112%

    No Known Activations