© 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. 97948
    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
     seamlessly
    -0.23
     cork
    -0.23
     mission
    -0.22
    çĶ¸
    -0.22
    ooter
    -0.21
     consideration
    -0.21
     cohesive
    -0.21
     fi
    -0.20
     lo
    -0.20
    å¯Ĵ
    -0.20
    POSITIVE LOGITS
    .sav
    0.25
    -rad
    0.24
    ä¿Ŀ
    0.23
    éri
    0.23
    æ°¡
    0.23
    prefer
    0.23
    saving
    0.22
    templ
    0.22
     pumps
    0.22
    æĢ»é¢Ŀ
    0.22
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.