© 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. 23929
    Prev
    Next
    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    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
    dr
    -0.26
    ä¸Ĭå²Ĺ
    -0.26
    _UNUSED
    -0.25
    髦
    -0.24
    Dr
    -0.24
    Elim
    -0.23
    romise
    -0.23
     Republic
    -0.23
    çĻ»åľº
    -0.23
    _dr
    -0.23
    POSITIVE LOGITS
     orders
    0.27
    æľºä¼ļ
    0.25
     pep
    0.25
    ä¸ŃåįİæĸĩåĮĸ
    0.24
    产åĵģçłĶåıij
    0.24
    è¯Ŀ说
    0.24
     Arab
    0.24
    è¿ĻéĩĮæĺ¯
    0.24
    antor
    0.23
    èµĦæºIJåħ±äº«
    0.23
    Activations Density 0.001%

    No Known Activations