© 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. 58058
    Prev
    Next
    INDEX
    Explanations

    letters

    np_max-act-logits · gemini-2.0-flash
    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
    éĢīæĭ©
    -0.33
    -select
    -0.32
     select
    -0.31
     Select
    -0.31
    select
    -0.31
    >Select
    -0.30
    éģ¸æĵĩ
    -0.30
    Selectable
    -0.29
     sele
    -0.29
     true
    -0.29
    POSITIVE LOGITS
     C
    0.49
    D
    0.48
     D
    0.47
    C
    0.46
    ï¼¢
    0.46
     B
    0.45
    ï¼£
    0.45
    B
    0.45
    Ａ
    0.43
    Ｄ
    0.42
    Activations Density 0.001%

    No Known Activations