© 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. 23-TRANSCODER-HP
    7. 25157
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĶĵ
    -0.28
     theirs
    -0.27
    ection
    -0.26
    GridColumn
    -0.26
    azÄĥ
    -0.26
     tren
    -0.25
     fact
    -0.24
     exactly
    -0.24
    opard
    -0.24
    åIJİåı°
    -0.24
    POSITIVE LOGITS
    nil
    0.29
    çģ«çĥ§
    0.26
    lit
    0.26
    æ¤ħ
    0.26
    uste
    0.25
    omat
    0.24
    åĨĻåĩº
    0.24
     AGRE
    0.24
     outputFile
    0.24
    .Nil
    0.24
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.