© 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. 88757
    Prev
    Next
    INDEX
    Explanations

    year

    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
    kus
    -0.29
    .assets
    -0.29
    èĮ±
    -0.27
     scl
    -0.26
    ilated
    -0.24
     sop
    -0.23
    AIL
    -0.23
    缸
    -0.23
    _Statics
    -0.23
    reak
    -0.23
    POSITIVE LOGITS
     alone
    0.28
    avier
    0.26
     resulting
    0.26
    ationally
    0.25
     depending
    0.25
    cv
    0.25
    éļıä¹ĭ
    0.24
    ĮĢ
    0.24
    æĥ¯ä¾ĭ
    0.24
    etsk
    0.23
    Activations Density 2.674%

    No Known Activations