© 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. 108771
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    /cpp
    -0.29
    éľĪ
    -0.27
    auté
    -0.26
    åĺ´åĶĩ
    -0.26
    lan
    -0.26
    -windows
    -0.25
    ackers
    -0.25
     acknowled
    -0.24
    .Plugin
    -0.24
    emm
    -0.24
    POSITIVE LOGITS
    ç´§
    0.34
    们
    0.30
    åı·
    0.29
    Unit
    0.29
     alike
    0.29
    tre
    0.29
    yh
    0.28
    pu
    0.27
    inge
    0.27
    大家
    0.27
    Activations Density 1.056%

    No Known Activations