© 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. 269
    Prev
    Next
    INDEX
    Explanations

    viruses/Virginia

    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
    æī£
    -0.31
    峡
    -0.27
    ileo
    -0.26
    drs
    -0.25
    jÄħ
    -0.25
    ä¼ijæģ¯
    -0.25
    æŀ
    -0.24
    åıijçĶŁçļĦ
    -0.24
    ymes
    -0.24
    lá
    -0.24
    POSITIVE LOGITS
    egal
    0.28
     treated
    0.25
    axed
    0.25
     curs
    0.25
    feed
    0.24
    æ³ĵ
    0.24
    iche
    0.24
    çĿĽ
    0.24
    roe
    0.23
     hub
    0.23
    Activations Density 0.015%

    No Known Activations