© 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. 31-TRANSCODER-HP
    7. 18137
    Prev
    Next
    INDEX
    Explanations

    Forum/code related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¤ãģį
    -0.28
     cycle
    -0.27
     Pou
    -0.26
    .databinding
    -0.26
    伺æľį
    -0.26
    cycle
    -0.25
    idable
    -0.25
    ervers
    -0.25
    缱
    -0.25
     env
    -0.25
    POSITIVE LOGITS
    Spec
    0.31
    港åĮº
    0.30
    nbsp
    0.29
     Peace
    0.29
    peace
    0.29
    å·¥ä¸ļ
    0.29
    si
    0.28
     si
    0.27
    港
    0.27
    Peace
    0.26
    Activations Density 1.337%

    No Known Activations