© 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. 111698
    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
    [:]
    -0.28
    vier
    -0.26
    æĨij
    -0.25
    ä»Ģä¹Īä¸ľè¥¿
    -0.25
    tica
    -0.25
     cognition
    -0.25
    thing
    -0.25
     Titanic
    -0.24
    iza
    -0.23
    æĦŁ
    -0.23
    POSITIVE LOGITS
    oven
    0.28
    å¹´ä¹ĭä¹ħ
    0.27
    çIJĨ
    0.26
    andy
    0.26
    èIJ¥éĢł
    0.26
     multiline
    0.25
    åĢĴ
    0.24
    orney
    0.24
    èIJ¥éĢłèī¯å¥½
    0.23
    hints
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.