© 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. 41153
    Prev
    Next
    INDEX
    Explanations

    computer networking and devices

    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
    æī¹
    -0.28
     slur
    -0.25
    ases
    -0.25
    KG
    -0.25
    ox
    -0.25
    çľģæķĻèĤ²
    -0.24
    IES
    -0.24
     Slash
    -0.24
    ÑģÑĥд
    -0.24
    typeof
    -0.23
    POSITIVE LOGITS
    驱
    0.29
    æŃ¥
    0.27
    åº
    0.27
    é©
    0.26
    ç«Ļ
    0.26
     étape
    0.26
     Concent
    0.25
    _WIN
    0.25
    (patch
    0.25
    å±Ĥ级
    0.24
    Activations Density 0.005%

    No Known Activations