© 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. 30257
    Prev
    Next
    INDEX
    Explanations

    another

    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
    irim
    -0.29
    åİĦ
    -0.28
    ä¸Ģå¼Ģå§ĭå°±
    -0.28
    çķĮçļĦ
    -0.27
     al
    -0.26
    æĸŃ
    -0.26
     threads
    -0.25
    erior
    -0.25
     Hot
    -0.25
     la
    -0.24
    POSITIVE LOGITS
    acad
    0.30
    soever
    0.27
    å·¦åı³
    0.27
     deal
    0.26
    apter
    0.25
    fällig
    0.25
    adesh
    0.25
    _FRE
    0.25
    -than
    0.24
    lasting
    0.24
    Activations Density 1.304%

    No Known Activations