© 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. 23827
    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
    念
    -0.31
     tob
    -0.28
    ç®ĢåİĨ
    -0.27
    帽
    -0.27
    èĩªèº«
    -0.27
    anas
    -0.27
     PMC
    -0.26
    åľ°ä¸Ĭ
    -0.26
    åľ°ä¸Ń
    -0.25
     Bord
    -0.25
    POSITIVE LOGITS
    erty
    0.30
     accordingly
    0.28
    Syn
    0.27
    _initializer
    0.26
     insets
    0.25
    æĺ¶
    0.25
    代åŃķ
    0.24
    roof
    0.24
    istani
    0.24
     Witt
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.