© 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. 12731
    Prev
    Next
    INDEX
    Explanations

    lack of experience or ability

    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
    åį«çĶŁ
    -0.20
    getMethod
    -0.20
    çĸı
    -0.20
     exemplary
    -0.19
    éĥ½ä¸įæķ¢
    -0.18
    æĸĩæĺİ
    -0.18
    [__
    -0.18
     careful
    -0.18
    ä¸įçķĻ
    -0.17
    Decl
    -0.17
    POSITIVE LOGITS
    åħ·ä½ĵ
    0.23
    缴æİ¥
    0.21
    eref
    0.21
    å®ŀéĻħ
    0.21
    åħ¬å¼Ģåıij
    0.20
     ìĪĺì§ij
    0.19
    rogram
    0.19
    ¶Ī
    0.19
    æѤ类
    0.19
    obao
    0.19
    Activations Density 0.010%

    No Known Activations