© 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. 31-TRANSCODER-HP
    7. 18298
    Prev
    Next
    INDEX
    Explanations

    technical automation instructions

    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
     sal
    -0.36
     Sal
    -0.31
     delic
    -0.29
    æĶ¾è¿Ľ
    -0.28
    å±ħ
    -0.28
     cig
    -0.27
    é¦Ļ
    -0.27
    .sal
    -0.26
     Mob
    -0.25
    Sm
    -0.25
    POSITIVE LOGITS
    ISTA
    0.29
    ADR
    0.28
     inverse
    0.28
    tright
    0.27
     inversion
    0.27
    éĥ½å¸Ĥ
    0.27
    hest
    0.26
     bull
    0.25
    terra
    0.25
     invers
    0.25
    Activations Density 5.912%

    No Known Activations