© 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. 162691
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    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
    ess
    -0.28
    åIJĪ
    -0.28
    nia
    -0.26
    代çIJĨ
    -0.25
     joint
    -0.25
    lection
    -0.25
    aight
    -0.24
    ass
    -0.24
     Scroll
    -0.23
    SUP
    -0.23
    POSITIVE LOGITS
    次ãģ®
    0.29
    æľªæĿ¥
    0.29
    åĴĮå¹³
    0.27
    æľªæĿ¥çļĦ
    0.27
    éķ¿åŁİ
    0.25
    erten
    0.25
     Taken
    0.25
     future
    0.25
    DidChange
    0.25
     futures
    0.24
    Activations Density 0.002%

    No Known Activations