© 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. 18668
    Prev
    Next
    INDEX
    Explanations

    thesis

    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
    DSA
    -0.29
    åºķå±Ĥ
    -0.27
     left
    -0.27
    Orm
    -0.26
    _left
    -0.26
    èļ£
    -0.25
    ãģŀ
    -0.25
    åīįæıIJæĺ¯
    -0.25
    LV
    -0.25
     Left
    -0.25
    POSITIVE LOGITS
    åIJĪæĪIJ
    0.36
     Synthetic
    0.35
    syn
    0.35
     Syn
    0.35
    Syn
    0.34
     syn
    0.33
     synthes
    0.32
     synthesis
    0.32
     synthetic
    0.31
     synthesized
    0.31
    Activations Density 0.088%

    No Known Activations