© 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. 9403
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    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
    неÑĤ
    -0.28
    ạm
    -0.26
     suit
    -0.25
    dap
    -0.25
    æĭIJ
    -0.25
    -cancel
    -0.24
    åħ³èĬĤ
    -0.24
    -heading
    -0.24
    JP
    -0.24
    uit
    -0.23
    POSITIVE LOGITS
    обÑīа
    0.26
    anter
    0.25
    erce
    0.25
     descendant
    0.24
     breathable
    0.24
    urope
    0.23
     enforcement
    0.23
    utive
    0.23
    boxes
    0.23
    LayoutConstraint
    0.23
    Activations Density 0.000%

    No Known Activations