© 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. 18720
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     pitching
    -0.32
    èĦ±åıij
    -0.26
    archy
    -0.24
     ((((
    -0.24
    xdf
    -0.24
    accom
    -0.23
     last
    -0.23
    ptest
    -0.23
     Viewing
    -0.23
     Crawford
    -0.23
    POSITIVE LOGITS
    GRES
    0.27
    å·¾
    0.26
    éĺĥ
    0.26
    è¯Ŀé¢ĺ
    0.25
    好äºĭ
    0.25
    bound
    0.25
    ä¸Ģ级
    0.25
    settings
    0.25
     programmes
    0.25
    ëĤ®
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.