© 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. 89483
    Prev
    Next
    INDEX
    Explanations

    speed

    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
    åģ¾
    -0.28
    ä¸įå¿ħ
    -0.27
    usr
    -0.27
    atism
    -0.26
    á»Ļ
    -0.26
    ä¿IJ
    -0.26
    Verb
    -0.25
     inclusive
    -0.25
    ç¾½
    -0.25
     ETA
    -0.25
    POSITIVE LOGITS
    å°ıæŶåīį
    0.27
    &action
    0.26
     whispers
    0.25
     mann
    0.25
    acie
    0.25
    acciones
    0.25
    Ñģал
    0.25
    /msg
    0.25
    =data
    0.25
     NAS
    0.24
    Activations Density 12.119%

    No Known Activations