© 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. 99276
    Prev
    Next
    INDEX
    Explanations

    early

    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
    ErrorHandler
    -0.29
    åIJ¬åIJ¬
    -0.26
    .struts
    -0.26
    моÑĢ
    -0.25
    åĬ©
    -0.25
    меÑĤÑĢ
    -0.23
    Ease
    -0.23
     ease
    -0.23
    ndx
    -0.22
    gro
    -0.22
    POSITIVE LOGITS
    ablish
    0.32
     years
    0.29
    ities
    0.28
    anter
    0.26
    hart
    0.26
    rem
    0.26
     rem
    0.26
    ä¸ķ
    0.25
    è¾Ī
    0.25
    imates
    0.25
    Activations Density 0.123%

    No Known Activations