© 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. 89403
    Prev
    Next
    INDEX
    Explanations

    eters

    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
     kla
    -0.25
    YN
    -0.24
    nis
    -0.24
    æĸ¹å¼ıè¿Ľè¡Į
    -0.24
     Pork
    -0.23
    èĢģ人家
    -0.23
     Laf
    -0.23
    gom
    -0.23
     fla
    -0.23
    idel
    -0.23
    POSITIVE LOGITS
    ested
    0.27
     bre
    0.25
    ç»Ŀ对
    0.25
    èµ°åħ¥
    0.24
     ÑģпÑĢав
    0.24
    _GRE
    0.24
     monot
    0.23
    lish
    0.23
     wre
    0.23
    åħ½
    0.23
    Activations Density 13.878%

    No Known Activations