© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12649
    Prev
    Next
    INDEX
    Explanations

    English and language

    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
    .coord
    -0.20
    /pub
    -0.20
    ilon
    -0.19
    å¥
    -0.19
    Neighbor
    -0.18
    دا
    -0.18
    ToSend
    -0.18
    empt
    -0.18
    culture
    -0.18
    æī¾å·¥ä½ľ
    -0.18
    POSITIVE LOGITS
    Assignable
    0.23
    åĵ®
    0.23
    -option
    0.22
    éħįéŁ³
    0.21
    åĬ£
    0.20
    option
    0.20
    ä»ħä¾Ľ
    0.20
    éĢī项
    0.20
     options
    0.20
     option
    0.20
    Activations Density 0.006%

    No Known Activations