© 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. 107575
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    社ä¼ļåıijå±ķ
    -0.29
     Ih
    -0.28
    lus
    -0.25
    âu
    -0.25
    äºķ
    -0.25
    è¯Ŀ
    -0.25
    ç»ıæµİåıijå±ķ
    -0.25
     Mathematics
    -0.25
    为äºĨ
    -0.24
    mars
    -0.24
    POSITIVE LOGITS
    patch
    0.27
    åģľçīĮ
    0.27
    oeff
    0.26
    è¹Ĭ
    0.26
    istique
    0.26
    ãĤ¹ãĤ¿ãĥ¼
    0.26
    çĶŁæķĪ
    0.26
     overloaded
    0.25
    åºķ
    0.25
    iores
    0.25
    Activations Density 1.020%

    No Known Activations