© 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. 16741
    Prev
    Next
    INDEX
    Explanations

    bank names and online services

    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
    åıªè§ģ
    -0.20
     Elliott
    -0.20
    ICT
    -0.19
    ä¼´
    -0.18
    æ°¸åĪ©
    -0.18
    /accounts
    -0.18
    ำ
    -0.18
    _errno
    -0.17
     Daw
    -0.17
    abel
    -0.17
    POSITIVE LOGITS
    åĦĢ
    0.20
    _mapped
    0.19
    ahi
    0.19
    rama
    0.19
    仪
    0.19
    oul
    0.18
    itemap
    0.18
    omi
    0.18
    ution
    0.17
    (dynamic
    0.17
    Activations Density 0.400%

    No Known Activations