© 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. 30-TRANSCODER-HP
    7. 96078
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®īä¸ľå°¼
    -0.27
    æ°ĶåĬ¿
    -0.26
     disproportion
    -0.26
    ngen
    -0.26
    CLICK
    -0.25
     Crate
    -0.25
    .randn
    -0.24
    åı¬
    -0.24
    toi
    -0.24
     scale
    -0.23
    POSITIVE LOGITS
    adic
    0.29
    .lu
    0.29
    ether
    0.28
    äºĮ代
    0.28
    izzo
    0.26
    oub
    0.26
    ensch
    0.26
    ç®ħ
    0.26
    lement
    0.25
    ünk
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.