© 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. 40788
    Prev
    Next
    INDEX
    Explanations

    diverse documents

    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
     lined
    -0.28
    éļĨ
    -0.27
    ecret
    -0.26
    ACHE
    -0.26
    亿
    -0.26
     recalled
    -0.25
     Hour
    -0.25
     scorer
    -0.24
    /mit
    -0.24
     Mercy
    -0.24
    POSITIVE LOGITS
    åĪĢ
    0.30
    ório
    0.25
    annel
    0.25
    .ops
    0.25
     minds
    0.25
    ä¸Ģ款
    0.25
    ToFront
    0.24
    å±Ĩ
    0.24
    æŀª
    0.24
    èĩĢ
    0.24
    Activations Density 0.065%

    No Known Activations