© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88427
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    ertiary
    -0.28
     privileges
    -0.26
    ç¥Ń
    -0.25
    cil
    -0.24
    pcodes
    -0.24
     +↵↵
    -0.23
    olvable
    -0.23
    ضر
    -0.23
     Reyes
    -0.23
    compatible
    -0.23
    POSITIVE LOGITS
    еÑĢж
    0.27
    åĬ³åĬ¡
    0.26
    ä¿¡æģ¯åħ¬å¼Ģ
    0.25
     add
    0.25
     LED
    0.25
    agh
    0.25
    å°Ĩ继ç»Ń
    0.24
    issa
    0.24
    _led
    0.23
    天河
    0.23
    Activations Density 2.500%

    No Known Activations