© 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. 35-TRANSCODER-HP
    7. 40022
    Prev
    Next
    INDEX
    Explanations

    routes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨä¼ļ
    -0.28
     backed
    -0.26
    æģį
    -0.26
    ç¾ŀ
    -0.25
    èĥł
    -0.24
     thừa
    -0.24
    è¿Ļä¸ĢçĤ¹
    -0.24
    sep
    -0.24
     ÑģбоÑĢ
    -0.23
    paren
    -0.23
    POSITIVE LOGITS
    oute
    0.47
     route
    0.47
    route
    0.46
     routing
    0.45
     routes
    0.45
     Routes
    0.45
    routing
    0.43
     Routing
    0.42
    -route
    0.42
    (route
    0.41
    Activations Density 0.035%

    No Known Activations