© 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. 12-TRANSCODER-HP
    7. 24198
    Prev
    Next
    INDEX
    Explanations

    ah

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    渺
    -0.28
     Marg
    -0.25
     лид
    -0.25
    稿
    -0.25
    ÙģاÙĤ
    -0.25
     nghi
    -0.24
    нее
    -0.24
    Marg
    -0.24
    	va
    -0.24
    olf
    -0.24
    POSITIVE LOGITS
    太平
    0.31
    parable
    0.27
    lete
    0.27
    uren
    0.27
    bourg
    0.27
     ward
    0.26
     Greene
    0.25
    -par
    0.25
    arez
    0.25
    éĥ½éľĢè¦ģ
    0.25
    Activations Density 0.000%

    No Known Activations