© 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. 23-TRANSCODER-HP
    7. 24542
    Prev
    Next
    INDEX
    Explanations

    Challenges and difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hog
    -0.28
    åIJ¸å¼ķäºĨ
    -0.27
    lez
    -0.26
    usch
    -0.26
    鸿
    -0.25
    èĩªåѦ
    -0.25
    误解
    -0.24
    没äºĭ
    -0.24
     Alexand
    -0.24
     Alexa
    -0.24
    POSITIVE LOGITS
    ım
    0.34
     guarded
    0.31
    rote
    0.28
     dotted
    0.26
     cover
    0.26
     dine
    0.26
    anal
    0.26
    imity
    0.25
    eda
    0.25
    shal
    0.24
    Activations Density 0.002%

    No Known Activations