© 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. 24-TRANSCODER-HP
    7. 150938
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¹²èĦĨ
    -0.30
    çĶļèĩ³è¿ŀ
    -0.26
     sme
    -0.25
     вообÑīе
    -0.25
     пи
    -0.24
    å±ħçĦ¶
    -0.24
     Verse
    -0.24
    пи
    -0.24
     outsiders
    -0.24
     singled
    -0.24
    POSITIVE LOGITS
     baud
    0.27
    çģ°
    0.26
    HEAD
    0.25
    åĸľ
    0.25
    éĥ¨
    0.25
    Compilation
    0.25
    ]='
    0.24
    ariat
    0.24
    éĥģ
    0.24
    ColumnInfo
    0.24
    Activations Density 2.219%

    No Known Activations

    This feature has no known activations.