© 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. 8960
    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
     stamps
    -0.27
    æĥľ
    -0.26
    çĭ¸
    -0.25
    åīį身
    -0.25
    é£İåħī
    -0.24
    履约
    -0.24
    æīŃ
    -0.24
    -strip
    -0.24
    okie
    -0.24
     stamp
    -0.24
    POSITIVE LOGITS
    å®ļå¾ĭ
    0.26
    -next
    0.26
    verse
    0.25
     begging
    0.25
    abama
    0.24
     again
    0.24
    íķĺê²łìĬµëĭĪëĭ¤
    0.24
    again
    0.24
    ¤í
    0.23
    forth
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.