© 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. 96330
    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
     Curse
    -0.30
    CEED
    -0.27
    agara
    -0.27
    extent
    -0.26
    CBS
    -0.26
    edly
    -0.25
     Regents
    -0.25
    ä¸ĭæīĭ
    -0.25
     seperate
    -0.25
    ajas
    -0.25
    POSITIVE LOGITS
    宽
    0.32
    对æĪij
    0.29
    ugin
    0.28
     â
    0.25
    ents
    0.24
    .localization
    0.24
     both
    0.24
    еÑģÑĤ
    0.24
    åı£
    0.24
    reflect
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.