© 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. 40292
    Prev
    Next
    INDEX
    Explanations

    staying current/updated

    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
    ANGO
    -0.30
    ython
    -0.27
    åºĬ
    -0.26
    .flags
    -0.25
    åIJĽ
    -0.25
    çĨĻ
    -0.25
    itals
    -0.24
     path
    -0.24
    ä¸Ģéĥ¨
    -0.24
    ä»ĸæĺ¯
    -0.24
    POSITIVE LOGITS
    лег
    0.26
    ulse
    0.25
    versed
    0.24
     adamant
    0.24
    Shares
    0.24
    aiser
    0.24
    ä¹ĹãĤĬ
    0.24
     createState
    0.24
    Stamp
    0.24
    ardless
    0.24
    Activations Density 1.875%

    No Known Activations