© 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. 88525
    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
    èĵĦ
    -0.32
     Pages
    -0.27
    åŁ¹èĤ²
    -0.25
    /sbin
    -0.25
     Phonetic
    -0.24
    ç½ij讯
    -0.23
    esian
    -0.23
    æīĭå¥Ĺ
    -0.23
     Harness
    -0.23
     Streams
    -0.23
    POSITIVE LOGITS
     vac
    0.29
     vacuum
    0.27
    ive
    0.27
    hard
    0.26
    vac
    0.26
    rot
    0.25
     aim
    0.24
    /*@
    0.24
    pute
    0.24
    DetailView
    0.24
    Activations Density 13.415%

    No Known Activations

    This feature has no known activations.