© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30488
    Prev
    Next
    INDEX
    Explanations

    organic compounds

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    俳
    -0.28
     flipping
    -0.25
    admins
    -0.25
    acies
    -0.25
    好æĦŁ
    -0.24
    oes
    -0.24
     голоÑģ
    -0.24
    олÑĮзоваÑĤ
    -0.23
    edo
    -0.23
    atically
    -0.23
    POSITIVE LOGITS
     arma
    0.29
    observable
    0.26
    arma
    0.26
     geral
    0.26
    cube
    0.25
     press
    0.25
    nex
    0.25
    éĻ¤å°ĺ
    0.24
     pcb
    0.24
     Rubin
    0.24
    Activations Density 0.594%

    No Known Activations