© 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. 97906
    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
    鼶ç¢İ
    -0.28
     ICommand
    -0.25
     continu
    -0.24
     Entry
    -0.24
     mention
    -0.23
     Emp
    -0.23
     entries
    -0.23
    jp
    -0.23
     carve
    -0.23
     resp
    -0.23
    POSITIVE LOGITS
    裳
    0.26
    ENS
    0.25
     joining
    0.24
     turned
    0.24
    NSS
    0.24
     hob
    0.24
    èīº
    0.24
    ÅĦ
    0.23
    ÑĦин
    0.23
    çļĦåħ·ä½ĵ
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.