© 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. 108730
    Prev
    Next
    INDEX
    Explanations

    Mont

    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
    ctic
    -0.28
     native
    -0.27
     k
    -0.26
    æ±ŁåĮĹ
    -0.25
    æ²¥
    -0.25
     phá
    -0.25
    Cop
    -0.25
     localObject
    -0.25
     Golden
    -0.24
     GOLD
    -0.24
    POSITIVE LOGITS
    aqu
    0.25
    ikers
    0.25
    æĪIJ人
    0.24
    èĮı
    0.24
    izons
    0.23
    ië
    0.23
    æŶæķĪ
    0.23
    aq
    0.23
    izioni
    0.23
     dzi
    0.23
    Activations Density 0.026%

    No Known Activations