© 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. 11304
    Prev
    Next
    INDEX
    Explanations

    blood group typing

    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
    æĬĵ
    -0.21
    _length
    -0.19
    ForObject
    -0.19
    çŁŃçŁŃ
    -0.19
    kop
    -0.19
    åĩ³
    -0.18
    çĿĢéĩį
    -0.18
    æĬĵä½ı
    -0.18
    argon
    -0.18
    =length
    -0.18
    POSITIVE LOGITS
    è¡Ģ
    0.22
    uos
    0.20
    è¡Ģ液
    0.20
     nale
    0.19
    æłĩè¯Ĩ
    0.19
    Compatibility
    0.19
     tattoo
    0.19
    ä¸įéĢļ
    0.18
    patibility
    0.18
     blood
    0.18
    Activations Density 0.062%

    No Known Activations