© 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. 18-TRANSCODER-HP
    7. 89778
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĢ¾
    -0.31
    ampie
    -0.28
    bots
    -0.27
    åĮħæĭ¬
    -0.25
    utches
    -0.25
    RFC
    -0.25
    éĻIJåĪ¶
    -0.24
     undergraduate
    -0.24
    书记
    -0.24
     Presidents
    -0.24
    POSITIVE LOGITS
    emplate
    0.27
    upe
    0.26
    isma
    0.26
    æīįæĺ¯çľŁæŃ£
    0.25
    å¸Ĥåľºä¸»ä½ĵ
    0.25
    _extract
    0.24
    为åĩĨ
    0.24
     (%)
    0.24
    affected
    0.24
     Extraction
    0.24
    Activations Density 0.113%

    No Known Activations

    This feature has no known activations.