© 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. 33-TRANSCODER-HP
    7. 52577
    Prev
    Next
    INDEX
    Explanations

    cloud

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ĥ¤
    -0.30
    åİŁåĪĻä¸Ĭ
    -0.26
    说åĪ°
    -0.26
     kob
    -0.25
    为空
    -0.25
    çīĩ
    -0.25
     En
    -0.24
    JJ
    -0.24
    ее
    -0.24
    Cog
    -0.24
    POSITIVE LOGITS
    äºij
    0.83
    éĽ²
    0.65
     cloud
    0.56
     clouds
    0.53
    cloud
    0.52
     Cloud
    0.51
    -cloud
    0.49
    Cloud
    0.46
    æĹ¥
    0.45
     æĽ
    0.44
    Activations Density 0.026%

    No Known Activations