© 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. 7449
    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
    orted
    -0.29
    implementation
    -0.29
    åŁŃ
    -0.28
    ique
    -0.27
    移æ¤į
    -0.27
    转移
    -0.26
    秣
    -0.25
    asan
    -0.25
     Volt
    -0.24
    ãĤ¿ãĤ¤ãĥŁãĥ³ãĤ°
    -0.24
    POSITIVE LOGITS
     Benson
    0.27
    ÑĩеÑģÑĤво
    0.26
    ))==
    0.25
     Coff
    0.25
    çĩĬ
    0.24
    hound
    0.24
    LETE
    0.24
    =https
    0.24
    ç»ıæµİæįŁå¤±
    0.23
    温馨
    0.23
    Activations Density 0.612%

    No Known Activations

    This feature has no known activations.