© 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. 25-TRANSCODER-HP
    7. 108566
    Prev
    Next
    INDEX
    Explanations

    colleges and lymphoma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ики
    -0.28
    eve
    -0.27
    é£ĺ
    -0.25
    æ°¾
    -0.25
    nings
    -0.25
    mA
    -0.24
     stakes
    -0.24
    lide
    -0.24
     windows
    -0.23
    otyp
    -0.23
    POSITIVE LOGITS
    heck
    0.30
    èĩ³äºİ
    0.28
    ÅŁi
    0.25
    Ñħа
    0.25
    æł¡
    0.24
    åģ¥åº·çļĦ
    0.24
     projekt
    0.24
    ems
    0.24
    åįĴ
    0.23
    inois
    0.23
    Activations Density 0.195%

    No Known Activations