© 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. 18031
    Prev
    Next
    INDEX
    Explanations

    protocol or network

    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
     Reflex
    -0.30
    mith
    -0.28
    åĤį
    -0.27
    .CreateIndex
    -0.26
    ihn
    -0.25
    åºıå¹ķ
    -0.24
    .unsqueeze
    -0.24
    witter
    -0.24
    åĢ©
    -0.24
    .ask
    -0.24
    POSITIVE LOGITS
     forwards
    0.28
    erra
    0.28
     forward
    0.27
    ujemy
    0.27
    -controls
    0.27
     fly
    0.27
    讹
    0.26
    ownt
    0.26
     controls
    0.25
     entities
    0.25
    Activations Density 1.020%

    No Known Activations