© 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. 10753
    Prev
    Next
    INDEX
    Explanations

    Share on other sites

    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
    RS
    -0.20
    ä¸Ģ座
    -0.20
    itar
    -0.20
    �s
    -0.20
    &amp
    -0.19
    akes
    -0.19
    ATES
    -0.18
    åĽŃ
    -0.18
    Pes
    -0.18
    Bo
    -0.18
    POSITIVE LOGITS
    иж
    0.20
    ç»ĵå©ļ
    0.19
    ä¸įæĺİ
    0.18
    ели
    0.18
    æīĵæŃ»
    0.18
    éĿ
    0.18
    ãĤĵãģ§ãģĻãģĮ
    0.18
    è²Ĭ
    0.17
    ä¸į稳å®ļ
    0.17
    andum
    0.17
    Activations Density 0.001%

    No Known Activations