© 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. 89768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ocity
    -0.29
    åĮħåĽ´
    -0.28
    grave
    -0.28
    常åĬ¡
    -0.26
    Ł³
    -0.25
    æŃ¢ãĤģ
    -0.25
    Advertis
    -0.24
    æķŀ
    -0.24
     пÑĢогноз
    -0.23
    semble
    -0.23
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.27
    ording
    0.25
    atsby
    0.25
    ä½Ļ家
    0.25
    ture
    0.25
    寤
    0.25
    ords
    0.24
    å¤Ħå¤Ħ
    0.24
    Dos
    0.24
     Os
    0.23
    Activations Density 1.038%

    No Known Activations

    This feature has no known activations.