© 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. 24263
    Prev
    Next
    INDEX
    Explanations

    (

    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
    athi
    -0.30
     bout
    -0.29
    æıĨ
    -0.25
     âľĵ
    -0.25
     shape
    -0.25
    è§ŀ
    -0.24
    åī¯æľ¬
    -0.24
     fourth
    -0.24
    åıijå±ķéĺ¶æ®µ
    -0.24
    ccount
    -0.23
    POSITIVE LOGITS
     ogl
    0.28
    ç«Łæĺ¯
    0.26
    溢
    0.25
    以èĩ³äºİ
    0.25
    æĮĩå¼ķ
    0.25
     sept
    0.25
    æĺİå¹´
    0.24
     Trainer
    0.24
    说å®ŀè¯Ŀ
    0.24
     anyway
    0.23
    Activations Density 0.001%

    No Known Activations