© 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. 41027
    Prev
    Next
    INDEX
    Explanations

    symptoms

    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
    rip
    -0.27
    ãĤľ
    -0.27
    rape
    -0.26
     flop
    -0.26
    asel
    -0.26
     accr
    -0.25
    rish
    -0.25
    umped
    -0.24
     timelines
    -0.24
    çļĦä¸ĢäºĽ
    -0.24
    POSITIVE LOGITS
     Programming
    0.28
    (pattern
    0.28
    çĭŃçªĦ
    0.27
    èIJ½åľ¨
    0.27
    é»ĺå¥ij
    0.27
    çļĦåĬ¨ä½ľ
    0.26
    aber
    0.26
    Programming
    0.26
    åıĮåIJij
    0.26
    historic
    0.26
    Activations Density 0.216%

    No Known Activations