© 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. 31-TRANSCODER-HP
    7. 19669
    Prev
    Next
    INDEX
    Explanations

    if, when (conditionals)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     no
    -0.34
    no
    -0.33
    _no
    -0.30
    izes
    -0.29
    	no
    -0.28
    (no
    -0.28
     not
    -0.27
     NOI
    -0.27
    izing
    -0.26
     sendData
    -0.26
    POSITIVE LOGITS
     need
    0.36
     integrated
    0.33
     properly
    0.32
     implemented
    0.32
    è¿ĺéľĢè¦ģ
    0.31
     taught
    0.31
    need
    0.31
    Integrated
    0.30
    ä¹ŁéľĢè¦ģ
    0.30
    éľĢè¦ģ
    0.29
    Activations Density 0.774%

    No Known Activations