© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162848
    Prev
    Next
    INDEX
    Explanations

    grammar and word usage

    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
    inbox
    -0.29
    ä¹ħ
    -0.28
    burst
    -0.27
    bur
    -0.26
     ATV
    -0.25
    .setTexture
    -0.25
    avan
    -0.25
    äºijéĽĨ
    -0.24
    梯éĺŁ
    -0.24
    exampleInput
    -0.23
    POSITIVE LOGITS
     English
    0.33
    åĶ
    0.30
     Lif
    0.30
    idi
    0.28
     doc
    0.27
     hor
    0.26
    èĭ±æĸĩ
    0.26
    常çĶ¨çļĦ
    0.26
     hack
    0.26
     today
    0.26
    Activations Density 0.007%

    No Known Activations