© 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. 25-TRANSCODER-HP
    7. 109036
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angkan
    -0.26
    溯
    -0.25
    EventListener
    -0.25
    ronics
    -0.25
    istica
    -0.25
    .htm
    -0.25
    ’app
    -0.25
    ificados
    -0.24
    егод
    -0.24
    ihad
    -0.24
    POSITIVE LOGITS
     SSR
    0.26
     Kab
    0.26
     separation
    0.26
    æŁIJ个
    0.26
    ob
    0.24
     OB
    0.24
    	ob
    0.24
    åĪĨ离
    0.24
    sg
    0.24
    datagrid
    0.24
    Activations Density 0.943%

    No Known Activations

    This feature has no known activations.