© 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. 22-TRANSCODER-HP
    7. 98426
    Prev
    Next
    INDEX
    Explanations

    Code and programming text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =o
    -0.28
    aning
    -0.26
    aned
    -0.26
    ãģĮãĤī
    -0.26
    åijĬ
    -0.25
    潦
    -0.25
    à¸Īำà¸ģ
    -0.25
    .TryParse
    -0.24
    minate
    -0.24
     Geschichte
    -0.24
    POSITIVE LOGITS
     would
    0.71
    would
    0.63
     Would
    0.60
     hypothetical
    0.58
    Would
    0.55
     hypoth
    0.44
     würde
    0.43
    设æĥ³
    0.43
     hätte
    0.42
     zou
    0.41
    Activations Density 0.008%

    No Known Activations