© 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. 161904
    Prev
    Next
    INDEX
    Explanations

    Later

    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
     further
    -0.28
    åĨįæĿ¥
    -0.27
    isco
    -0.27
    oot
    -0.27
     Further
    -0.27
    å°Ķ
    -0.27
     existence
    -0.26
    onta
    -0.26
    ok
    -0.24
    Further
    -0.24
    POSITIVE LOGITS
    äºĨåIJĹ
    0.27
    ethyst
    0.26
    IDER
    0.26
     moved
    0.25
    [System
    0.25
    -blood
    0.25
    ä¸Ģ次次
    0.24
    zeichnet
    0.24
    sold
    0.24
     MAS
    0.24
    Activations Density 0.055%

    No Known Activations