© 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. 39885
    Prev
    Next
    INDEX
    Explanations

    scientific and medical 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
    á»ħn
    -0.27
    nicas
    -0.26
    è´¨éĩıå®īåħ¨
    -0.26
    caled
    -0.24
    phere
    -0.24
    ifikasi
    -0.24
    èĭĮ
    -0.24
     ...)↵
    -0.23
     Rudd
    -0.23
    sphere
    -0.23
    POSITIVE LOGITS
    Va
    0.27
    _NEAR
    0.26
    entially
    0.26
     RVA
    0.26
    cx
    0.26
    ingly
    0.25
    ately
    0.24
     Wa
    0.24
    oured
    0.24
     INA
    0.24
    Activations Density 0.564%

    No Known Activations