© 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. 30179
    Prev
    Next
    INDEX
    Explanations

    improvement and progression

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĬ³
    -0.29
    iones
    -0.28
    ignored
    -0.27
    é¥Ń
    -0.26
    swire
    -0.26
    à¹ģà¸Ļะ
    -0.26
    å®Į
    -0.25
     pháºŃn
    -0.25
    åħ¨éĥ½
    -0.25
    ág
    -0.25
    POSITIVE LOGITS
     SHALL
    0.28
     Operator
    0.27
     Binder
    0.24
     Pen
    0.24
     operator
    0.23
     ż
    0.23
    lify
    0.23
     aggregates
    0.23
    伯
    0.23
    åı°å·ŀ
    0.23
    Activations Density 2.093%

    No Known Activations