© 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. 11185
    Prev
    Next
    INDEX
    Explanations

    short films

    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
    ÙħصÙĦØŃØ©
    -0.42
    Ø£Ùĩد
    -0.42
    ÙħÙģاÙĪضات
    -0.42
    ÙħصطÙģ
    -0.41
    ÙħصÙĦ
    -0.40
    Ø£ÙĪضاع
    -0.40
    ÙħصاÙĦØŃ
    -0.40
    Ùħغرب
    -0.39
    استÙģ
    -0.37
    إص
    -0.36
    POSITIVE LOGITS
    0.28
    **
    0.25
    -
    0.25
    <|endoftext|>
    0.24
    _
    0.24
    1
    0.23
    ...
    0.23
    Âł
    0.22
    "
    0.22
    2
    0.22
    Activations Density 16.642%

    No Known Activations