© 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. 54551
    Prev
    Next
    INDEX
    Explanations

    Code and special symbols

    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
    Not in Any Lists

    No Comments

    Negative Logits
     F
    -0.60
    F
    -0.54
     E
    -0.54
    E
    -0.54
    G
    -0.51
     G
    -0.48
    éŃı
    -0.43
    .E
    -0.40
    _F
    -0.39
    ï¼¥
    -0.39
    POSITIVE LOGITS
    ĶåĽŀ
    0.26
    Åľ
    0.24
    Vac
    0.24
    afx
    0.23
     Baz
    0.23
    xAD
    0.23
    Q
    0.23
    ivable
    0.23
    çIJīçĴĥ
    0.22
    tools
    0.22
    Activations Density 0.025%

    No Known Activations