© 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. 88619
    Prev
    Next
    INDEX
    Explanations

    switch

    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
    frag
    -0.29
    çĸĸ
    -0.27
    åĪijäºĭ责任
    -0.26
    èĢ¸
    -0.26
    à¹ģà¸ŀà¸Ĺย
    -0.25
    .synthetic
    -0.25
    perimental
    -0.25
    该éĻ¢
    -0.24
    驳
    -0.24
    fine
    -0.24
    POSITIVE LOGITS
    anel
    0.28
    ucer
    0.27
    æĥķ
    0.26
    åıĹ
    0.26
    adol
    0.26
     indoors
    0.25
    HEN
    0.25
    ANEL
    0.24
    åĻ¨
    0.24
    æį·
    0.24
    Activations Density 17.953%

    No Known Activations