© 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. 89896
    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
    _then
    -0.27
    è·£
    -0.24
    assis
    -0.24
    weets
    -0.24
    veled
    -0.24
    DialogContent
    -0.23
    æ®Ľ
    -0.23
    æĬĢèĥ½åŁ¹è®Ń
    -0.23
    æĹĭ
    -0.23
    ért
    -0.23
    POSITIVE LOGITS
    .Priority
    0.28
     Priority
    0.27
    heroes
    0.25
    å°±è¶Ĭ
    0.25
    æĹ©æĹ¥
    0.25
     Hou
    0.25
     [<
    0.24
    å°½æĹ©
    0.24
    flux
    0.24
    æįı
    0.24
    Activations Density 0.707%

    No Known Activations

    This feature has no known activations.