© 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. 95366
    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
    ITS
    -0.26
    å²ĺ
    -0.25
    æĪ·ç±į
    -0.24
    çĪIJ
    -0.24
    ISON
    -0.24
    éģİä¾Ĩ
    -0.24
    åĨ°ç®±
    -0.24
    èªł
    -0.24
    çİ
    -0.24
    è¿Ļ座
    -0.23
    POSITIVE LOGITS
    unta
    0.25
     tÃłn
    0.25
    ŀ
    0.24
    éľĨ
    0.24
     Compound
    0.23
    psc
    0.23
    ione
    0.23
    çĭ¬åħ·
    0.23
    group
    0.23
    æĦıè§ģåıįé¦Ī
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.