© 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. 131101
    Prev
    Next
    INDEX
    Explanations

    Code or technical documentation

    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
     pitched
    -0.27
    ä¸Ģåij³
    -0.26
    spl
    -0.26
     vtx
    -0.24
    å®īåħ¨ä¿Ŀéļľ
    -0.23
    èĭ«
    -0.23
    ä½Ĩ对äºİ
    -0.23
     triplet
    -0.23
    ä¼ij
    -0.23
    æģ
    -0.22
    POSITIVE LOGITS
     Ack
    0.26
    jes
    0.25
    here
    0.24
    å¤Ļ
    0.24
    =en
    0.24
     ici
    0.23
    &S
    0.23
    åĵģæł¼
    0.22
    ãĤŃãĥ£
    0.22
    åĵģ
    0.22
    Activations Density 0.135%

    No Known Activations