© 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. 12-TRANSCODER-HP
    7. 22535
    Prev
    Next
    INDEX
    Explanations

    neural networks and deep learning

    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
    çľĭå¾Ĺ
    -0.30
    ForeColor
    -0.25
     min
    -0.25
    åİħ
    -0.24
     Fraser
    -0.24
     scaleFactor
    -0.24
    å¹²é¢Ħ
    -0.24
    Lf
    -0.23
     todd
    -0.23
     maxSize
    -0.23
    POSITIVE LOGITS
    "..
    0.25
    istributor
    0.25
     Meteor
    0.25
    |=↵
    0.24
    å´Ħ
    0.24
     Progress
    0.24
    ination
    0.23
    reat
    0.23
    auf
    0.23
    meteor
    0.23
    Activations Density 0.004%

    No Known Activations