© 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. 95633
    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
    frag
    -0.27
     readers
    -0.26
    elling
    -0.25
    >>(
    -0.24
    aku
    -0.24
    EXTERN
    -0.24
    读èĢħ
    -0.24
    æİĮéŨ
    -0.23
     dem
    -0.23
    ahun
    -0.23
    POSITIVE LOGITS
    åĵ¨
    0.28
    æīŃ
    0.28
    sing
    0.26
    -China
    0.26
     mill
    0.25
    alous
    0.25
     abl
    0.25
    /twitter
    0.24
    çĦļçĥ§
    0.24
    ä¼łå¯¼
    0.24
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.