© 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. 12031
    Prev
    Next
    INDEX
    Explanations

    controlled by or converted to

    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
     mach
    -0.20
    _GC
    -0.19
     opport
    -0.19
    arm
    -0.19
    åķ°
    -0.18
    ÏĤ
    -0.18
    ä»»ä½ķæŶåĢĻ
    -0.18
    nis
    -0.17
    yp
    -0.17
     tim
    -0.17
    POSITIVE LOGITS
    ofday
    0.19
    otland
    0.19
    读åIJİ
    0.18
    _dll
    0.18
    обоÑĢоÑĤ
    0.18
    ï¸
    0.17
     занÑıÑĤ
    0.17
    usta
    0.17
    _plugin
    0.17
    DisplayStyle
    0.17
    Activations Density 0.114%

    No Known Activations