© 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. 9-TRANSCODER-HP
    7. 29793
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ory
    -0.28
    WAYS
    -0.28
    owler
    -0.26
    æ¯ı个人çļĦ
    -0.26
    crast
    -0.26
    erals
    -0.25
    worm
    -0.25
    urers
    -0.25
    çļĦè¶ĭåĬ¿
    -0.25
    ittings
    -0.24
    POSITIVE LOGITS
    ä¸ĭ鼨
    0.28
    麻çĥ¦
    0.27
     sob
    0.25
    _BOOLEAN
    0.25
    èĦ±ç¦»
    0.24
    æIJ
    0.24
    è¯ŀ
    0.23
    äºŃ
    0.23
    æ¼±
    0.23
     Band
    0.23
    Activations Density 5.509%

    No Known Activations