© 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. 32-TRANSCODER-HP
    7. 41793
    Prev
    Next
    INDEX
    Explanations

    scientific solutions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģç¬Ķ
    -0.31
     pinch
    -0.26
    ä¸Ģ个
    -0.25
     Tot
    -0.25
    -services
    -0.25
     mw
    -0.24
    æŃĥ
    -0.24
     negatives
    -0.24
    methods
    -0.24
     roots
    -0.24
    POSITIVE LOGITS
    .portal
    0.32
    она
    0.28
    ophil
    0.27
    ophys
    0.26
    ä¼ģ
    0.25
    人大
    0.25
    LayoutPanel
    0.24
    pai
    0.24
    onald
    0.24
    .ax
    0.24
    Activations Density 0.009%

    No Known Activations