© 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. 88710
    Prev
    Next
    INDEX
    Explanations

    Code snippets/technical documentation

    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
    æĵį
    -0.26
     Covenant
    -0.25
    каÑı
    -0.24
    anners
    -0.23
    顺
    -0.23
     gyr
    -0.23
    康
    -0.23
    cobra
    -0.23
     Learned
    -0.23
    æŦ
    -0.22
    POSITIVE LOGITS
    йÑĤ
    0.26
     authenticate
    0.26
     abbreviated
    0.25
    é³Į
    0.25
    ighton
    0.24
    authenticate
    0.24
    atk
    0.24
    延éķ¿
    0.24
    lander
    0.24
     Patrol
    0.24
    Activations Density 2.219%

    No Known Activations