© 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. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40508
    Prev
    Next
    INDEX
    Explanations

    tus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĮ¨
    -0.30
    бо
    -0.26
    èģĮæĿĥ
    -0.26
    æłī
    -0.25
     tus
    -0.25
    幫
    -0.25
    帮
    -0.24
    è°ĥéħį
    -0.24
     اÙĦØ£Ùħر
    -0.24
     restart
    -0.23
    POSITIVE LOGITS
    whelming
    0.28
    ìłľ
    0.26
    eric
    0.25
    CADE
    0.25
    averse
    0.25
    ä¸Ńå¼ı
    0.24
     eup
    0.24
    :image
    0.24
    ingles
    0.24
    imeo
    0.23
    Activations Density 1.466%

    No Known Activations