© 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. 19-TRANSCODER-HP
    7. 8910
    Prev
    Next
    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .fixed
    -0.28
     divers
    -0.27
    ivers
    -0.27
     Hed
    -0.26
    ç»ıèIJ¥çIJĨ念
    -0.25
     ['.
    -0.24
    aire
    -0.24
    榧
    -0.24
    åĨľåī¯
    -0.24
    -0.24
    POSITIVE LOGITS
     MPS
    0.26
     som
    0.26
    cery
    0.25
     PSP
    0.25
     SOP
    0.24
     foc
    0.24
    som
    0.24
    spiracy
    0.24
    好è¯Ħ
    0.24
    åħ¬åħ±èµĦæºIJ
    0.24
    Activations Density 0.034%

    No Known Activations