© 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. 88620
    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
    amac
    -0.28
    å¹²åĺĽ
    -0.28
    èĤĵ
    -0.27
    xic
    -0.26
    ismic
    -0.25
    åģļä»Ģä¹Ī
    -0.25
    åĮ»ç§ij
    -0.25
     веÑģÑĮ
    -0.24
    ´Ģ
    -0.24
    èĻ¢
    -0.24
    POSITIVE LOGITS
    ennen
    0.28
     Bennett
    0.26
    assa
    0.26
    arem
    0.25
    archives
    0.25
     Garr
    0.24
    çľ¼è§Ĵ
    0.24
    ç»Ĩ
    0.24
     Benn
    0.24
     Benny
    0.24
    Activations Density 4.954%

    No Known Activations

    This feature has no known activations.