© 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. 24875
    Prev
    Next
    INDEX
    Explanations

    events over time

    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
    ä¸İä¸ŃåĽ½
    -0.28
    sky
    -0.28
    äºİ
    -0.26
    å¹»
    -0.26
     kole
    -0.25
    åħī
    -0.25
    å¥Ĺ
    -0.25
    峨
    -0.24
    çIJĨæĥ³
    -0.24
     Lucia
    -0.24
    POSITIVE LOGITS
     period
    0.41
    åĪĩãĤĮ
    0.29
    -period
    0.29
    Quiet
    0.28
    aji
    0.28
     periods
    0.27
     lifetime
    0.27
     duration
    0.27
     lasting
    0.27
    period
    0.27
    Activations Density 0.009%

    No Known Activations