© 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. 312
    Prev
    Next
    INDEX
    Explanations

    Kab

    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
    ing
    -0.26
    使ãģĪãĤĭ
    -0.25
    øj
    -0.24
    .spi
    -0.24
    atre
    -0.23
    outil
    -0.23
    ätz
    -0.23
    IFY
    -0.23
    zzo
    -0.22
    unger
    -0.22
    POSITIVE LOGITS
    ç¡ķ士åѦä½į
    0.24
    istr
    0.24
    èĩªæĿ¥æ°´
    0.24
    h
    0.23
    åıĹåĪ°äºĨ
    0.23
    inate
    0.23
     Brother
    0.23
    amel
    0.23
    oom
    0.23
     Creator
    0.23
    Activations Density 0.017%

    No Known Activations