© 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. 13525
    Prev
    Next
    INDEX
    Explanations

    warm summer, weather, waters, relations

    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
    naire
    -0.24
    UNCH
    -0.17
    Ùħا
    -0.16
    odont
    -0.16
    UnderTest
    -0.16
    sic
    -0.15
    rame
    -0.15
     Lime
    -0.14
     chặt
    -0.14
    ún
    -0.14
    POSITIVE LOGITS
    ingly
    0.23
    -hearted
    0.22
    à¹Ĩ
    0.21
    -blood
    0.21
    ish
    0.20
    enstein
    0.19
    人å¿ĥ
    0.19
    oon
    0.19
    åīĤ
    0.19
    orary
    0.18
    Activations Density 0.013%

    No Known Activations