© 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. 12762
    Prev
    Next
    INDEX
    Explanations

    allow, Allow, conditions, format

    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
    çĨı
    -0.21
    SplitOptions
    -0.21
    VMLINUX
    -0.20
    unge
    -0.20
    prime
    -0.20
    å¥Ħ
    -0.20
    индив
    -0.20
    asca
    -0.19
    à¸Ļà¹Ĥย
    -0.19
    å®ĥ
    -0.19
    POSITIVE LOGITS
    æ¼ı
    0.24
    è¦ģ说
    0.19
    _fault
    0.19
    Instances
    0.19
    át
    0.18
    ধ
    0.18
    é¦ĸåĪĽ
    0.18
    literal
    0.18
    Ñħ
    0.17
    defs
    0.17
    Activations Density 0.001%

    No Known Activations