© 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. 10868
    Prev
    Next
    INDEX
    Explanations

    feet

    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
    er
    -0.23
    ãģĦãĤĭ
    -0.23
    ity
    -0.22
    ships
    -0.22
    land
    -0.20
    ship
    -0.20
    erÃŃa
    -0.20
    erate
    -0.19
    иÑĤеÑĤ
    -0.19
    ized
    -0.18
    POSITIVE LOGITS
    /or
    0.21
    ÑģÑĤÑĮ
    0.19
    ãģ®ãģ¯
    0.18
    TING
    0.18
    eeee
    0.17
    ãģ®ãģĮ
    0.17
    Ùĭ
    0.17
    ä¸Ģå¹´
    0.17
    anny
    0.16
    ãģĩ
    0.16
    Activations Density 0.017%

    No Known Activations