© 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. 108286
    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
    çݯå¢ĥ
    -0.27
    é¦į
    -0.27
    åij½åIJį
    -0.26
     Divide
    -0.25
    ç¼ĺ
    -0.25
    coc
    -0.25
     Armenian
    -0.25
    åĤ»
    -0.25
    计åĪĴ
    -0.25
    å¹»
    -0.25
    POSITIVE LOGITS
    .cls
    0.29
    è¿Ļè¾¹
    0.26
    Vectorizer
    0.26
    )[-
    0.26
    -toggler
    0.25
    è¿Ļ件äºĭæĥħ
    0.25
    lycer
    0.25
     DECL
    0.25
     calculations
    0.24
    llib
    0.24
    Activations Density 0.053%

    No Known Activations

    This feature has no known activations.