© 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. 9210
    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
    çĭ·
    -0.27
    åijĬè¯ī她
    -0.26
    agina
    -0.25
    åī¯
    -0.25
    .News
    -0.25
    ì§Ģ를
    -0.24
    åĺı
    -0.24
     ÙħÙĨزÙĦ
    -0.24
    zie
    -0.24
     inquire
    -0.24
    POSITIVE LOGITS
    sig
    0.25
    andan
    0.25
     Wil
    0.25
    Wil
    0.24
    ierce
    0.23
    ssi
    0.23
    opo
    0.23
     (!((
    0.23
    urt
    0.23
     Freeze
    0.22
    Activations Density 0.106%

    No Known Activations

    This feature has no known activations.