© 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. 40244
    Prev
    Next
    INDEX
    Explanations

    scientific/technical 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
    (#)
    -0.26
    骨æŀ¶
    -0.25
     horns
    -0.25
    æĮ¡
    -0.24
     polÃŃtica
    -0.23
    åĴ¥
    -0.23
     :(
    -0.23
    èĭ¦
    -0.23
    åı¥
    -0.23
    à¤ł
    -0.23
    POSITIVE LOGITS
    å±ħ家
    0.29
     intr
    0.28
    entr
    0.27
     signals
    0.26
    intr
    0.26
    >{$
    0.26
    followers
    0.24
    ÑģÑĤвенно
    0.24
     Equality
    0.24
    éĺľ
    0.24
    Activations Density 0.268%

    No Known Activations