© 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. 9-TRANSCODER-HP
    7. 29799
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSObject
    -0.26
    auce
    -0.25
    finity
    -0.25
     parentNode
    -0.24
    holding
    -0.24
    ooke
    -0.24
     NST
    -0.24
    ject
    -0.24
    azu
    -0.23
    éĢ£
    -0.23
    POSITIVE LOGITS
     moll
    0.28
    åĴ«
    0.28
     tú
    0.26
    èĪ
    0.26
    çĸij
    0.25
    èĢģå®ŀ
    0.25
    communic
    0.24
    åı¯çĸij
    0.24
    .ServiceModel
    0.24
    ä¿Ħ
    0.24
    Activations Density 22.780%

    No Known Activations

    This feature has no known activations.