© 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. 88881
    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
    TER
    -0.26
    空
    -0.26
    çī¹
    -0.25
    åŃIJ
    -0.25
    imum
    -0.25
    }*/↵↵
    -0.24
    èģĶåIJĪä¼ļ
    -0.24
     tongue
    -0.24
    uckle
    -0.24
    BER
    -0.24
    POSITIVE LOGITS
    weis
    0.28
     unthinkable
    0.27
    blr
    0.27
    ä¸įçķĻ
    0.27
    åIJijãģį
    0.27
    åħ¼é¡¾
    0.26
    æĴµ
    0.26
    ä¸ĢæĿ¯
    0.25
    åĽŀäºĭ
    0.25
    æĥ³è¿ĩ
    0.25
    Activations Density 5.821%

    No Known Activations

    This feature has no known activations.