© 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. 130831
    Prev
    Next
    INDEX
    Explanations

    Addressing someone in writing

    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
     NDEBUG
    -0.28
    åĬŁè¯¾
    -0.27
    çªģåĽ´
    -0.26
     Monument
    -0.25
    失踪
    -0.25
     Funds
    -0.23
    atto
    -0.23
     Surround
    -0.23
    äºĭæĥħ
    -0.23
    deal
    -0.23
    POSITIVE LOGITS
    éģĵ
    0.29
    çĶ³è¯·äºº
    0.26
    .refs
    0.26
    åij
    0.26
    och
    0.26
    ainer
    0.25
    -provider
    0.25
    ots
    0.25
    åħĪçĶŁ
    0.24
    _PHP
    0.24
    Activations Density 0.009%

    No Known Activations