© 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. 111844
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æIJł
    -0.27
    å¤Ħå¤Ħ
    -0.27
    gain
    -0.27
    å±ŀå®ŀ
    -0.26
    åħ¥åºĵ
    -0.25
    tures
    -0.25
    jsx
    -0.25
    ĥģ
    -0.24
    raid
    -0.24
    llib
    -0.24
    POSITIVE LOGITS
     inf
    0.29
     rule
    0.28
     Rule
    0.27
    大éģĵ
    0.27
     Rules
    0.26
     nod
    0.26
     trouble
    0.26
     optionally
    0.25
     Safe
    0.25
    ouble
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.