© 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. 27-TRANSCODER-HP
    7. 57017
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨį
    -0.25
    称
    -0.24
    âĢ¦↵↵↵
    -0.23
    TEM
    -0.23
    money
    -0.23
    ()},
    -0.23
    äºĨä¸Ģ份
    -0.23
     excerpts
    -0.23
    çĻ¼
    -0.23
    ])),
    -0.23
    POSITIVE LOGITS
     abs
    0.27
     corner
    0.27
    keh
    0.27
    _ABS
    0.25
    äºŃ
    0.24
     BaseModel
    0.24
    éĩİçĶŁ
    0.24
    pan
    0.24
    çķĮ
    0.23
    大è§Ħ模
    0.23
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.