© 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. 9050
    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
     orth
    -0.31
    æĽĻ
    -0.29
    ence
    -0.29
    cre
    -0.26
     rescued
    -0.26
    cut
    -0.25
    orth
    -0.25
    cr
    -0.24
    ibox
    -0.24
     reson
    -0.24
    POSITIVE LOGITS
    yen
    0.30
    è¿ŀè¿ŀ
    0.27
    Êı
    0.26
    aming
    0.25
    ployment
    0.25
     NodeType
    0.25
     Fulton
    0.24
    ilt
    0.24
     Pocket
    0.24
    zing
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.