© 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. 33-TRANSCODER-HP
    7. 54026
    Prev
    Next
    INDEX
    Explanations

    school admissions and exams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Screen
    -0.27
     View
    -0.27
    offs
    -0.27
    _props
    -0.26
     imageSize
    -0.25
    æ±Łå±±
    -0.25
     Peninsula
    -0.25
    prop
    -0.24
    <View
    -0.24
    ores
    -0.24
    POSITIVE LOGITS
    箨
    0.26
     blankets
    0.25
    unist
    0.25
    åħļåĴĮ
    0.25
     Mam
    0.25
    urat
    0.24
     rotations
    0.24
     tÆ°á»Ŀng
    0.24
    è¿IJèIJ¥åķĨ
    0.24
     Minh
    0.24
    Activations Density 0.031%

    No Known Activations