© 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. 8610
    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
    issance
    -0.27
    assa
    -0.27
    ilm
    -0.24
     feature
    -0.24
    è´£
    -0.24
    feature
    -0.24
    acea
    -0.23
    èµĥ
    -0.23
     corresponding
    -0.23
    assin
    -0.23
    POSITIVE LOGITS
    ÑĤан
    0.28
    åĬłåħ¥äºĨ
    0.24
    ä¾Ľç»Ļ侧
    0.23
    æĬ«éľ²
    0.23
    åįģåŃĹ
    0.23
     Rad
    0.22
    ADR
    0.22
    xp
    0.22
    ery
    0.22
    å§Ĭ妹
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.