© 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. 33-TRANSCODER-HP
    7. 52992
    Prev
    Next
    INDEX
    Explanations

    scientific/medical imaging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tÃŃ
    -0.25
     VF
    -0.25
     GLenum
    -0.25
    -addon
    -0.24
    代çIJĨ人
    -0.24
     Rotterdam
    -0.24
    åįĬ个
    -0.24
     RestClient
    -0.24
     Conflict
    -0.23
     Curtain
    -0.23
    POSITIVE LOGITS
    trans
    0.27
     transc
    0.27
    åı¦è¡Į
    0.26
    go
    0.25
    uns
    0.25
    æ´®
    0.25
    Ws
    0.24
     bios
    0.24
    NOTE
    0.24
    èķĻ
    0.24
    Activations Density 0.045%

    No Known Activations