© 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. 9226
    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
     Ach
    -0.26
    enko
    -0.26
    rat
    -0.25
    è·Łå¥¹
    -0.25
    åĪ«
    -0.25
    :checked
    -0.25
    _GAP
    -0.24
     ach
    -0.24
    gon
    -0.24
    ouse
    -0.24
    POSITIVE LOGITS
     retaining
    0.29
    ä¹Ĥ
    0.28
    æĪªæŃ¢
    0.28
    arges
    0.27
     turn
    0.26
    æĦı大
    0.26
    æĥº
    0.25
     NS
    0.25
    iring
    0.25
    -NLS
    0.25
    Activations Density 0.134%

    No Known Activations

    This feature has no known activations.