© 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. 89223
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and initials

    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
    èĥĮ
    -0.30
    Æ°u
    -0.27
    Z
    -0.27
    èĥĮçĿĢ
    -0.27
     tand
    -0.26
     breakthrough
    -0.25
     Z
    -0.25
    xz
    -0.24
    éļ¾
    -0.24
    -Z
    -0.23
    POSITIVE LOGITS
     physic
    0.28
    åıŁ
    0.27
    ÑĦи
    0.26
    pole
    0.26
    marshall
    0.25
    _msgs
    0.25
    åĮºåŁŁæĢ§
    0.24
     ÑĢоман
    0.24
    夷
    0.24
    岬
    0.24
    Activations Density 4.893%

    No Known Activations