© 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. 22-TRANSCODER-HP
    7. 128996
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å½
    -0.33
    å°Ķ
    -0.29
    ATABASE
    -0.25
    onna
    -0.25
    çĪ¾
    -0.25
    onz
    -0.25
     wid
    -0.24
     Installing
    -0.24
     Lane
    -0.24
     installing
    -0.24
    POSITIVE LOGITS
    ynth
    0.27
    çķĮ
    0.25
    æĢĢæĬ±
    0.25
    åĪĨéħį
    0.25
    ufen
    0.24
    óg
    0.24
    ucus
    0.24
    Äĥm
    0.23
     fête
    0.23
    åĩĢåľŁ
    0.23
    Activations Density 0.011%

    No Known Activations