© 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. 108294
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tees
    -0.28
    itchen
    -0.27
    æĺĵ
    -0.27
    åĿĽ
    -0.26
     Alter
    -0.25
    itis
    -0.24
     Mesa
    -0.24
    thouse
    -0.24
    uppy
    -0.24
    åĽºå®ļçļĦ
    -0.24
    POSITIVE LOGITS
    éŀĺ
    0.30
    ĽĦ
    0.29
    æİĽ
    0.28
    å¥
    0.25
    æ½ľ
    0.25
     charg
    0.25
    AffineTransform
    0.24
    æĮĤ
    0.24
    fter
    0.24
    rac
    0.24
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.