© 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. 54400
    Prev
    Next
    INDEX
    Explanations

    scientific/chemical processes

    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
    ä¹³
    -0.27
    APER
    -0.27
     Vertical
    -0.26
    æħķ
    -0.25
    æķĽ
    -0.25
     nar
    -0.25
     Moor
    -0.24
    ¯¯¯¯
    -0.24
    agedList
    -0.24
     CPR
    -0.24
    POSITIVE LOGITS
     meter
    0.28
     metre
    0.27
    meter
    0.26
    åįĸç»Ļ
    0.26
     sold
    0.26
     suit
    0.26
     sells
    0.25
    FIT
    0.25
     ż
    0.25
    ak
    0.25
    Activations Density 0.061%

    No Known Activations