© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53932
    Prev
    Next
    INDEX
    Explanations

    Berlin, Germany

    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
    xDE
    -0.27
    夷
    -0.26
     appointment
    -0.24
    举
    -0.24
    .ylabel
    -0.24
    éĶ®
    -0.24
     pacman
    -0.24
    racial
    -0.24
    hang
    -0.24
    é¤
    -0.23
    POSITIVE LOGITS
     mil
    0.31
     sl
    0.29
    stri
    0.27
    æĭ·
    0.27
    abit
    0.25
     char
    0.24
    reo
    0.24
    åĢŁçĶ¨
    0.24
    å¼Ĥè®®
    0.24
    .isNull
    0.23
    Activations Density 0.018%

    No Known Activations