© 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. 24443
    Prev
    Next
    INDEX
    Explanations

    Technical documentation and internet 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
    bid
    -0.31
     bid
    -0.31
    ä¹Łè®©
    -0.28
    æĪijæĥ³
    -0.27
     bi
    -0.27
     Euros
    -0.26
    bi
    -0.25
     depress
    -0.25
    æĹ¥çĶµ
    -0.25
     sensed
    -0.24
    POSITIVE LOGITS
    getInstance
    0.29
    è»Ł
    0.23
     Summary
    0.23
    .Builder
    0.23
    ç¾½
    0.23
     ÐĽÐ¸
    0.23
    inality
    0.23
    _map
    0.23
    彧
    0.23
    arity
    0.23
    Activations Density 0.052%

    No Known Activations