© 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. 21953
    Prev
    Next
    INDEX
    Explanations

    technical context

    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
    æīĵçIJĥ
    -0.27
    äºĶä¸Ģ
    -0.26
    éĻª
    -0.26
    æŀķ
    -0.26
    æīĺ
    -0.25
    æµĩæ°´
    -0.25
    äºĶæĺŁ
    -0.25
    æī£
    -0.25
     Flat
    -0.25
     Tues
    -0.24
    POSITIVE LOGITS
    aland
    0.31
    追
    0.29
    al
    0.28
    -stage
    0.26
     stage
    0.25
    alink
    0.25
    ####
    0.25
    åı·çº¿
    0.24
     shred
    0.24
    äºĨå¤ļå°ij
    0.24
    Activations Density 0.001%

    No Known Activations