© 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. 41532
    Prev
    Next
    INDEX
    Explanations

    Painting and applying

    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
    URATION
    -0.28
    éĴ±
    -0.27
    anja
    -0.26
    交æį¢
    -0.26
    æѦæŀĹ
    -0.25
    undos
    -0.25
    OMET
    -0.25
    æĸ¯çī¹
    -0.25
     Ske
    -0.25
    éĮ¢
    -0.25
    POSITIVE LOGITS
     em
    0.32
    åĵģ
    0.28
    马åħĭ
    0.27
    ioxid
    0.26
     Mouth
    0.26
     var
    0.26
     oil
    0.26
    ën
    0.26
    ify
    0.25
     marker
    0.25
    Activations Density 0.004%

    No Known Activations