© 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. 30318
    Prev
    Next
    INDEX
    Explanations

    append

    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
     mean
    -0.29
     kaps
    -0.28
    å¤Ħå¤Ħéķ¿
    -0.27
    emean
    -0.27
     Mean
    -0.27
    çĶŁæŃ»
    -0.27
    mean
    -0.26
    ä¸ĩéĩĮ
    -0.26
     interrogation
    -0.26
     against
    -0.24
    POSITIVE LOGITS
    edis
    0.33
    è¸ı
    0.29
    onis
    0.29
    éĹª
    0.28
    éĹªåħī
    0.27
    posable
    0.27
    é¢Ħå¤ĩ
    0.26
    -flash
    0.25
    åĩºè®©
    0.25
     Jad
    0.25
    Activations Density 2.004%

    No Known Activations