© 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. 32-TRANSCODER-HP
    7. 41198
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     +:+
    -0.28
    dzi
    -0.27
    æIJģ
    -0.26
    _beh
    -0.26
    å¾·å°Ķ
    -0.25
    èµĭ
    -0.25
     DateTimeKind
    -0.24
    ENCED
    -0.24
    æĵħ
    -0.24
    DOC
    -0.24
    POSITIVE LOGITS
    xt
    0.34
    asan
    0.29
    çģ°
    0.27
    quiv
    0.25
     ComVisible
    0.25
    rem
    0.25
     ash
    0.25
     Ca
    0.24
    -ton
    0.24
    rams
    0.23
    Activations Density 0.006%

    No Known Activations