© 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. 95964
    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
    æł¼å¼ı
    -0.27
    è¿ģ
    -0.26
    å©Ĭ
    -0.25
    _SPEC
    -0.24
    act
    -0.24
    å½ĵ
    -0.24
    ãĥ¥
    -0.24
    -Language
    -0.24
    riteln
    -0.23
    spec
    -0.23
    POSITIVE LOGITS
    inx
    0.28
    åŁļ
    0.26
    gue
    0.25
    зол
    0.25
    nic
    0.25
    elian
    0.24
     refl
    0.24
    anel
    0.24
    nder
    0.24
    inc
    0.24
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.