© 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. 89827
    Prev
    Next
    INDEX
    Explanations

    Period / full stop

    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
    ox
    -0.27
    èĩ»
    -0.26
    flix
    -0.26
     Dön
    -0.26
    溱
    -0.25
    æıIJéĨĴ
    -0.25
    æ¹į
    -0.25
    rit
    -0.24
    ä¸įåIJĥ
    -0.24
    abb
    -0.24
    POSITIVE LOGITS
    ollapsed
    0.30
     BaseController
    0.28
    SURE
    0.26
    å¼ĤæĢ§
    0.26
    ysz
    0.25
     outsider
    0.25
    appendChild
    0.25
    ivity
    0.24
    !,↵
    0.24
    .constructor
    0.23
    Activations Density 0.324%

    No Known Activations