© 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. 40343
    Prev
    Next
    INDEX
    Explanations

    business/organizational context

    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
    ilitating
    -0.27
    éģ¿
    -0.25
    pur
    -0.25
    çĮ®
    -0.24
    ersion
    -0.24
     PropertyValue
    -0.24
     Span
    -0.24
    éĩĩ
    -0.24
     Puerto
    -0.24
    çłĶ究æīĢ
    -0.24
    POSITIVE LOGITS
     tall
    0.26
    -extra
    0.24
    CU
    0.24
    .Single
    0.24
    ys
    0.24
    ä¸ĢæŦ
    0.23
    ments
    0.23
    at
    0.23
    omatic
    0.23
     inner
    0.23
    Activations Density 0.874%

    No Known Activations