© 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
    2. Qwen3-4B
    3. 12-TRANSCODER-HP
    4. 22718
    Prev
    Next
    INDEX
    Explanations

    chemistry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XT
    -0.30
    å»·
    -0.28
    æłĩ
    -0.28
    æĻ¯
    -0.28
     Ext
    -0.26
     ext
    -0.25
    Ext
    -0.25
     обо
    -0.25
     installations
    -0.25
     perf
    -0.24
    POSITIVE LOGITS
    ÑĢÑĥÑĤ
    0.26
    سÙģ
    0.25
    éľ²å¤©
    0.25
    REDENTIAL
    0.24
    .ur
    0.24
    å¼ĢæĶ¾
    0.23
    åĢĮ
    0.23
     exited
    0.23
    ensus
    0.23
    çķİ
    0.23
    Activations Density 0.010%

    No Known Activations