© 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. 18067
    Prev
    Next
    INDEX
    Explanations

    political commentary

    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
    æ¶Ĥ
    -0.26
    æ¶Ĥå±Ĥ
    -0.26
     flashlight
    -0.26
     lug
    -0.25
    .figure
    -0.25
    åħīæ»ij
    -0.25
    ÑĨов
    -0.24
    phinx
    -0.24
     fim
    -0.24
    iece
    -0.23
    POSITIVE LOGITS
     America
    0.38
     Washington
    0.35
     Britain
    0.34
     Europe
    0.31
     France
    0.30
    Washington
    0.29
     England
    0.28
     trade
    0.28
    Hit
    0.28
    nav
    0.27
    Activations Density 3.059%

    No Known Activations