© 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. 52892
    Prev
    Next
    INDEX
    Explanations

    {

    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
    æīĵå¾Ĺ
    -0.27
     Lace
    -0.26
     Lap
    -0.26
    ields
    -0.26
    defs
    -0.25
     mocks
    -0.25
    .instance
    -0.25
    æĪŁ
    -0.24
    Lens
    -0.24
    åħ¥éĢī
    -0.24
    POSITIVE LOGITS
    isse
    0.28
    çĨ
    0.28
    éªħ
    0.26
    ober
    0.26
    eler
    0.25
     duplication
    0.24
    é«ĺ强度
    0.24
    ou
    0.24
    /games
    0.24
    ILLE
    0.24
    Activations Density 0.035%

    No Known Activations