© 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
    2. Qwen3-4B
    3. 22-TRANSCODER-HP
    4. 112362
    Prev
    Next
    INDEX
    Explanations

    Consider

    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
     rig
    -0.27
    trigger
    -0.25
    åĸĺ
    -0.25
     Rig
    -0.24
    wig
    -0.24
    俦
    -0.24
    çļĦæĪĺçķ¥
    -0.23
    dued
    -0.23
     strm
    -0.23
     counted
    -0.23
    POSITIVE LOGITS
    ung
    0.32
    ation
    0.30
    imum
    0.27
    ãĥ³ãĤ°
    0.26
    shi
    0.26
    ball
    0.26
    Ø©
    0.24
    ql
    0.24
    ìŀ¥
    0.24
    çŁ¥
    0.24
    Activations Density 0.008%

    No Known Activations