© 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. 107559
    Prev
    Next
    INDEX
    Explanations

    Phillipines

    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
     Barang
    -0.46
     barang
    -0.45
     Filipino
    -0.44
     ang
    -0.43
     Filip
    -0.42
     Philippines
    -0.41
    èı²å¾ĭ宾
    -0.40
     Manila
    -0.40
     philippines
    -0.39
    âĤ±
    -0.39
    POSITIVE LOGITS
    æ±ŁåĮĹ
    0.27
    çIJĨçĶ±
    0.26
    Whilst
    0.26
    ÑĪин
    0.26
     Hampshire
    0.25
    евиÑĩ
    0.25
    mpr
    0.25
    opian
    0.25
    .swap
    0.25
    eft
    0.25
    Activations Density 0.912%

    No Known Activations