© 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. 35-TRANSCODER-HP
    7. 40344
    Prev
    Next
    INDEX
    Explanations

    EM

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crud
    -0.27
     P
    -0.26
     ${↵
    -0.24
    æĢ»çIJĨ
    -0.24
    Appointment
    -0.24
     ..."↵
    -0.24
    天æĸĩ
    -0.23
    oland
    -0.23
    -0.23
    :",↵
    -0.23
    POSITIVE LOGITS
     sine
    0.32
    gradient
    0.30
     body
    0.30
    EZ
    0.29
     moments
    0.29
    less
    0.29
    stress
    0.29
     gradient
    0.29
    -body
    0.28
    rad
    0.28
    Activations Density 25.542%

    No Known Activations