© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7457
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bows
    -0.30
    бÑĢ
    -0.28
    ATORS
    -0.28
    åĬŀ好
    -0.28
    ieres
    -0.27
     breathing
    -0.25
    -entry
    -0.25
     turns
    -0.25
    æİ°
    -0.25
    EntryPoint
    -0.25
    POSITIVE LOGITS
    pragma
    0.28
    åĹŁ
    0.25
    vp
    0.25
    ç³Ł
    0.25
    èį£
    0.25
     Sv
    0.25
    alcon
    0.24
    Ñģлав
    0.24
    _vp
    0.24
    atively
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.