© 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. 15342
    Prev
    Next
    INDEX
    Explanations

    pr + endings like ian, akash, inski, ach, kov

    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
    ãģĮãĤī
    -0.21
    ãĥªãĥ³ãĤ°
    -0.19
    fter
    -0.18
    lets
    -0.18
    缦
    -0.17
    ä½Ĩåľ¨
    -0.17
    ortal
    -0.17
    clid
    -0.17
    iture
    -0.16
    人éĢł
    -0.16
    POSITIVE LOGITS
    ya
    0.21
    waves
    0.20
    iras
    0.18
    ãģĵãģ¨ãģĮãģ§ãģį
    0.18
    ãģĥ
    0.17
    gere
    0.17
    ila
    0.16
    noon
    0.16
    kan
    0.16
    bury
    0.16
    Activations Density 0.805%

    No Known Activations