© 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. 40320
    Prev
    Next
    INDEX
    Explanations

    Descriptive text

    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
    quent
    -0.25
    ulations
    -0.25
     exponentially
    -0.25
     regained
    -0.24
    isOk
    -0.24
    é³ŀ
    -0.23
     remembered
    -0.23
    oks
    -0.23
    头ä¸Ĭ
    -0.23
    æľºç¥¨
    -0.23
    POSITIVE LOGITS
    zag
    0.27
    å¾ģæ±ĤæĦıè§ģ
    0.26
    dirname
    0.26
     diffusion
    0.26
    ::__
    0.26
    lse
    0.25
    \Doctrine
    0.24
    åĵģ
    0.23
    .truth
    0.23
    pires
    0.23
    Activations Density 0.028%

    No Known Activations