© 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. 98011
    Prev
    Next
    INDEX
    Explanations

    addresses and codes

    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
    ste
    -0.30
    UID
    -0.28
    brig
    -0.27
    TH
    -0.26
    uid
    -0.26
    ensi
    -0.26
     brig
    -0.26
    avigation
    -0.26
    Tip
    -0.25
    imeo
    -0.25
    POSITIVE LOGITS
    .epoch
    0.26
    ä¹ī
    0.26
     religious
    0.25
    entials
    0.25
    .palette
    0.25
    ileged
    0.25
    inkle
    0.24
    峡
    0.24
    æĪ·
    0.23
    amental
    0.23
    Activations Density 0.005%

    No Known Activations