© 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. 24-TRANSCODER-HP
    7. 151330
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ings
    -0.32
    bone
    -0.28
    edList
    -0.26
    伪
    -0.26
    achable
    -0.25
    沧
    -0.25
     Lift
    -0.24
    è´Ń票
    -0.24
    IFT
    -0.24
     structure
    -0.24
    POSITIVE LOGITS
    åĹª
    0.31
     fend
    0.27
    转身
    0.27
     walls
    0.26
    æĦĪ
    0.25
    serter
    0.25
     fled
    0.25
     gated
    0.24
     tables
    0.24
    _fds
    0.24
    Activations Density 0.159%

    No Known Activations