© 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. 41326
    Prev
    Next
    INDEX
    Explanations

    Code specifications

    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
    etch
    -0.26
    truth
    -0.26
    quiet
    -0.26
    .PerformLayout
    -0.25
    allah
    -0.25
    loading
    -0.24
    icles
    -0.24
    weet
    -0.24
     truth
    -0.23
    lep
    -0.23
    POSITIVE LOGITS
    orer
    0.25
    uled
    0.24
    CKER
    0.24
    決
    0.24
    atedRoute
    0.23
    ISHED
    0.23
    ä¼ļå±ķ
    0.23
     soc
    0.23
    åıĸåĨ³äºİ
    0.23
     those
    0.22
    Activations Density 4.104%

    No Known Activations