© 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. 13634
    Prev
    Next
    INDEX
    Explanations

    vestibular

    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
    çļĭ
    -0.20
     autoComplete
    -0.20
    iscrim
    -0.19
    apro
    -0.18
    è£ĺ
    -0.18
    abez
    -0.18
    /native
    -0.17
     Jared
    -0.17
    ities
    -0.17
    èģĶåIJĪä¼ļ
    -0.17
    POSITIVE LOGITS
    çݯ
    0.19
    æĸĩæĺĮ
    0.19
    严èĤĥ
    0.19
    俸
    0.19
    rit
    0.19
    çĽĺ
    0.18
    IRM
    0.18
    icone
    0.18
    viz
    0.18
    ç´§åĩij
    0.18
    Activations Density 0.046%

    No Known Activations