© 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. 30-TRANSCODER-HP
    7. 96366
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iset
    -0.29
    mut
    -0.26
    æĸ¯åŁº
    -0.25
     altern
    -0.25
     Cree
    -0.25
    oglob
    -0.25
    _mut
    -0.25
    ä¸īåįģ
    -0.25
    åįķ项
    -0.25
    uese
    -0.24
    POSITIVE LOGITS
    éĶ®
    0.30
    hin
    0.30
     suspects
    0.28
    è¡Ķ
    0.26
    糸
    0.25
    AspNet
    0.25
    çŀ§
    0.25
    æĢĢ念
    0.24
    导èĪª
    0.24
    åѬ
    0.24
    Activations Density 0.040%

    No Known Activations

    This feature has no known activations.