© 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. 88538
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    ä½į
    -0.28
    eor
    -0.28
    ibilities
    -0.28
    ibi
    -0.27
    strap
    -0.27
    IPP
    -0.26
    icap
    -0.26
     enfer
    -0.25
    |"
    -0.25
    eled
    -0.24
    POSITIVE LOGITS
     tab
    0.27
    .struts
    0.25
    opes
    0.25
    åıĮåıĮ
    0.25
    NAV
    0.24
    odef
    0.24
    ation
    0.24
     crumbs
    0.24
     alone
    0.24
    adero
    0.24
    Activations Density 5.428%

    No Known Activations