© 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. 18-TRANSCODER-HP
    7. 89250
    Prev
    Next
    INDEX
    Explanations

    Architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.32
    allah
    -0.26
    ous
    -0.26
    links
    -0.26
    primary
    -0.26
    åIJĮç±»
    -0.24
     enumer
    -0.24
    缸éĤ»
    -0.23
     adj
    -0.23
    .done
    -0.23
    POSITIVE LOGITS
    åİĨåı²æĸĩåĮĸ
    0.27
    æĮĤçīĮ
    0.27
     Chem
    0.26
    _TW
    0.26
    _tw
    0.25
    æħ¢æħ¢åľ°
    0.25
    eres
    0.25
    _variance
    0.24
    wij
    0.24
    æĹ¥æ¸IJ
    0.24
    Activations Density 12.315%

    No Known Activations