© 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. 41007
    Prev
    Next
    INDEX
    Explanations

    Mixed texts, some about writing

    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
    oble
    -0.28
    cam
    -0.26
    è¯ķåīĤ
    -0.26
    è¾ħ
    -0.26
    ilib
    -0.26
    emption
    -0.25
     slips
    -0.25
    ellers
    -0.25
     casts
    -0.24
    å®Ŀè´µçļĦ
    -0.24
    POSITIVE LOGITS
    osaic
    0.26
    /png
    0.26
    ldb
    0.25
    éķ¿è¿ľ
    0.25
    izophren
    0.25
    西éĥ¨
    0.25
    lse
    0.24
    éķ¿ä¹ħ
    0.24
    -times
    0.24
    人次
    0.24
    Activations Density 1.171%

    No Known Activations