© 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. 32-TRANSCODER-HP
    7. 42814
    Prev
    Next
    INDEX
    Explanations

    coding/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    天æ°Ķ
    -0.44
     weather
    -0.43
    weather
    -0.40
    æ°ĶåĢĻ
    -0.39
    åĨ°
    -0.37
    .weather
    -0.37
    Weather
    -0.37
    /weather
    -0.35
    åĨ°éĽª
    -0.35
    åĨ»
    -0.35
    POSITIVE LOGITS
     severe
    0.34
    colon
    0.33
     mild
    0.32
     Mild
    0.29
     inc
    0.29
     severity
    0.28
    co
    0.27
     colon
    0.26
     VARIABLE
    0.26
    åıĺ
    0.26
    Activations Density 0.004%

    No Known Activations