© 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. 24961
    Prev
    Next
    INDEX
    Explanations

    are/is

    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
    ancy
    -0.28
     spur
    -0.27
    agr
    -0.27
     murm
    -0.27
    çī¹å®ļ
    -0.27
     specific
    -0.27
    incy
    -0.26
     marg
    -0.26
     marginal
    -0.26
     somehow
    -0.26
    POSITIVE LOGITS
     courtesy
    0.29
    å·²
    0.29
    å·²åľ¨
    0.28
    å°ļæľª
    0.28
     licensed
    0.27
    åĵģçīĮçļĦ
    0.27
     belum
    0.26
    欢è¿İæĤ¨
    0.26
    å®ŀä¹łçĶŁ
    0.26
     Äijá»Ļc
    0.26
    Activations Density 0.022%

    No Known Activations