© 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. 112389
    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
    edo
    -0.28
    BuilderInterface
    -0.28
     grub
    -0.26
    heel
    -0.25
    éĢĢåĩº
    -0.25
     crossing
    -0.24
    excel
    -0.24
     exit
    -0.24
     Crossing
    -0.24
    idos
    -0.24
    POSITIVE LOGITS
    ues
    0.25
    æĶ¶è´¹
    0.25
     charg
    0.25
    Unmount
    0.24
    ousel
    0.24
    elier
    0.24
    çĤ¹çĩĥ
    0.24
    纷纷表示
    0.24
     surprisingly
    0.24
    åŁİå¸Ĥ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.