© 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. 25-TRANSCODER-HP
    7. 108135
    Prev
    Next
    INDEX
    Explanations

    foreign graphemes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĸ²åĬ³
    -0.33
     stamped
    -0.28
     Maze
    -0.25
     bronze
    -0.25
     Kahn
    -0.25
    秾
    -0.25
     fatigue
    -0.25
    èIJĭ
    -0.25
    çĸ²
    -0.25
     padded
    -0.25
    POSITIVE LOGITS
    åľ°çIJĥ
    0.45
     Earth
    0.42
    大æ°Ķ
    0.40
    çļĦåľ°
    0.40
     NOAA
    0.38
    éģ¥
    0.38
    赤
    0.35
     vegetation
    0.35
     ge
    0.35
     crust
    0.35
    Activations Density 1.315%

    No Known Activations