© 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. 24580
    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
    ivas
    -0.28
    iele
    -0.26
    _gap
    -0.26
    rouch
    -0.26
    ocab
    -0.25
     ëĶ°ëĿ¼ìĦľ
    -0.25
    ç²ķ
    -0.24
     STYLE
    -0.24
     dens
    -0.24
    ilar
    -0.24
    POSITIVE LOGITS
    ä¸Ĭ线
    0.28
    çİĩè¾¾
    0.27
    yes
    0.27
    åĽ½æĥħ
    0.26
    缮çĿ¹
    0.25
    ye
    0.25
    (IOException
    0.24
    积累
    0.24
    缸è¿ŀ
    0.24
    èµ°ä¸ĭåİ»
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.