© 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. 11987
    Prev
    Next
    INDEX
    Explanations

    percentage

    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
    upo
    -0.21
    æĸ°çļĦä¸Ģ
    -0.19
     rtn
    -0.19
    .tap
    -0.18
    [of
    -0.18
    è´¯
    -0.17
    comed
    -0.17
    bish
    -0.17
     cigaret
    -0.16
    _UNS
    -0.16
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.24
    å·¦åı³
    0.22
    äºĨèĩªå·±çļĦ
    0.20
    è¶ħ
    0.19
    åħ¨åŁŁ
    0.19
     (!
    0.19
    ally
    0.18
    askan
    0.18
    说èĩªå·±
    0.18
    (!
    0.18
    Activations Density 0.032%

    No Known Activations