© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6357
    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
    ç¯ij
    -0.29
    aec
    -0.27
    çĶ»
    -0.26
    åĩłæŃ¥
    -0.26
    à¦Ľ
    -0.26
    modes
    -0.25
     Swift
    -0.25
    astered
    -0.25
    illions
    -0.24
    enary
    -0.24
    POSITIVE LOGITS
    缸
    0.30
    ohana
    0.27
     unmatched
    0.27
    bits
    0.26
    åħ«åŃĹ
    0.25
     odds
    0.25
     Un
    0.25
    éķ¿çĽ¸
    0.25
    exc
    0.25
    ozo
    0.25
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.