© 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. 98517
    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
    cas
    -0.25
    erot
    -0.25
    auga
    -0.24
     "."
    -0.24
    ircular
    -0.24
    "."
    -0.24
    ilk
    -0.23
    ucchini
    -0.23
    ulus
    -0.23
    oti
    -0.23
    POSITIVE LOGITS
    CAPE
    0.30
    VT
    0.28
     assort
    0.27
    åĩĢåĢ¼
    0.26
    ön
    0.26
     Liên
    0.25
    CAC
    0.25
     interception
    0.23
    —at
    0.23
    rastructure
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.