© 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. 18425
    Prev
    Next
    INDEX
    Explanations

    dep

    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
    bro
    -0.30
    çģµ
    -0.28
    istle
    -0.26
     Brush
    -0.26
     Roz
    -0.26
    eries
    -0.26
    arrant
    -0.26
    åĬ¨ä½ľ
    -0.26
     brushing
    -0.25
    ajaran
    -0.25
    POSITIVE LOGITS
    éĶ¹
    0.30
    nts
    0.28
    åİĭ缩
    0.26
     Compression
    0.26
    enaire
    0.26
    press
    0.25
    iselect
    0.25
    ken
    0.25
    mdat
    0.24
     Walton
    0.24
    Activations Density 0.012%

    No Known Activations