© 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. 110966
    Prev
    Next
    INDEX
    Explanations

    protection and support

    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
     universe
    -0.32
     Universe
    -0.30
     human
    -0.29
    ä¸Ĭå¸Ŀ
    -0.29
     Almighty
    -0.29
    .qual
    -0.26
     God
    -0.26
    åĵºä¹³
    -0.25
     sentient
    -0.25
     humans
    -0.25
    POSITIVE LOGITS
     pinch
    0.28
     franca
    0.27
     Synopsis
    0.26
     PSG
    0.25
    ODY
    0.25
    cery
    0.25
    OTS
    0.25
    éŨ
    0.24
    AQ
    0.24
    omens
    0.24
    Activations Density 0.001%

    No Known Activations