© 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. 27-TRANSCODER-HP
    7. 56945
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪĸå¤ļ
    -0.31
    packageName
    -0.27
    å·²ç»ıå¼Ģå§ĭ
    -0.27
    å¼Ģå§ĭäºĨ
    -0.27
    olas
    -0.26
    ktor
    -0.26
    deo
    -0.26
     cass
    -0.25
    RAM
    -0.25
    èĭ±æł¼
    -0.25
    POSITIVE LOGITS
    裳
    0.30
     åĬ
    0.27
     building
    0.27
     Assumes
    0.26
    cret
    0.25
    身边çļĦ
    0.25
    Cos
    0.24
     phon
    0.24
     writing
    0.24
    ens
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.