© 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. 96072
    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
    ByExample
    -0.27
    emens
    -0.26
     Blind
    -0.26
    主èIJ¥ä¸ļ
    -0.26
    blind
    -0.26
    itti
    -0.25
     subjects
    -0.25
    .fm
    -0.24
    ENCIL
    -0.24
    lix
    -0.24
    POSITIVE LOGITS
    ä½ľ
    0.32
    è¶ħ级
    0.28
    odox
    0.26
    ordova
    0.26
    itant
    0.25
     stretching
    0.25
    _sys
    0.25
    ç»ĵ论
    0.24
    LOUD
    0.24
    æľį
    0.24
    Activations Density 0.102%

    No Known Activations

    This feature has no known activations.