© 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. 12439
    Prev
    Next
    INDEX
    Explanations

    character traits

    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
    2
    -0.35
    1
    -0.35
    3
    -0.33
    4
    -0.32
    I
    -0.31
    :
    -0.31
    5
    -0.31
    6
    -0.31
     l
    -0.31
    8
    -0.30
    POSITIVE LOGITS
    ãĤ¢ãĤ¤ãĥĨ
    0.46
    èķĹ
    0.44
    楪
    0.43
    ãįī
    0.42
    ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥį
    0.42
     arsch
    0.42
    ãģĦãĤīãģ£
    0.41
    çŃ¥
    0.41
    ãĤŃãĥ£ãĥ³ãĥļ
    0.41
    ãģĶè¦
    0.41
    Activations Density 0.135%

    No Known Activations