© 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. 4-TRANSCODER-HP
    7. 184
    Prev
    Next
    INDEX
    Explanations

    battle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ialis
    -0.33
    ISTA
    -0.26
    ctions
    -0.25
    å°ģéĶģ
    -0.24
     leap
    -0.24
    setItem
    -0.23
    ingham
    -0.23
    alus
    -0.23
    iente
    -0.23
    ourg
    -0.23
    POSITIVE LOGITS
    æĹĭ
    0.32
    éı¡
    0.28
     fitting
    0.27
    åĿĽ
    0.26
     Rhino
    0.24
    éķľ
    0.24
    .fit
    0.23
    _Att
    0.23
    hv
    0.23
    åħļåĴĮåĽ½å®¶
    0.23
    Activations Density 0.064%

    No Known Activations