© 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. 10764
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    á»ij
    -0.20
    cling
    -0.19
    á»IJ
    -0.18
    ibia
    -0.18
    ê²°
    -0.17
    aji
    -0.17
    è¸Ĭè·ĥ
    -0.17
    éĸ£
    -0.17
    rot
    -0.17
    że
    -0.17
    POSITIVE LOGITS
     danmark
    0.19
    ä¸įåħ¬å¹³
    0.19
    èľ·
    0.19
     münchen
    0.19
    à¹Ģà¸Ł
    0.18
    paginator
    0.18
     norge
    0.18
     echang
    0.17
     Neighborhood
    0.17
     salopes
    0.17
    Activations Density 0.048%

    No Known Activations