© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97957
    Prev
    Next
    INDEX
    Explanations

    Numbers in legal/technical documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
     besides
    -0.28
     Disclaimer
    -0.26
    åģĩ
    -0.26
    æĪĴ
    -0.26
     Franz
    -0.26
    è¦ģ害
    -0.25
    chos
    -0.25
    apel
    -0.25
    ète
    -0.24
    çĽ¸ä¼¼
    -0.24
    POSITIVE LOGITS
    leton
    0.32
    izr
    0.28
    æĹĦ
    0.27
    TCHA
    0.26
    ibrator
    0.26
     em
    0.25
    åľī
    0.25
    .createObject
    0.24
    eways
    0.23
    .FLAG
    0.23
    Activations Density 0.017%

    No Known Activations