© 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. 53594
    Prev
    Next
    INDEX
    Explanations

    path-related

    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
    robe
    -0.26
    åľ¨çİ°åľº
    -0.25
    .Formatting
    -0.25
    velt
    -0.24
    æķ¢äºİ
    -0.23
    ÑĢин
    -0.23
    gran
    -0.23
    ä¼ij
    -0.23
    æĸĹ
    -0.23
    çīµå¼ķ
    -0.22
    POSITIVE LOGITS
     path
    1.35
    è·¯å¾Ħ
    1.30
    path
    1.20
    -path
    1.17
     Path
    1.16
    Path
    1.13
     paths
    1.13
    _path
    1.11
    .path
    1.05
    	path
    1.04
    Activations Density 0.333%

    No Known Activations