© 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. 25-TRANSCODER-HP
    7. 107808
    Prev
    Next
    INDEX
    Explanations

    data and specifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mut
    -0.30
    mut
    -0.28
     energy
    -0.27
    ERM
    -0.26
     oil
    -0.25
    rek
    -0.25
     syn
    -0.25
    -0.25
    erm
    -0.25
    let
    -0.24
    POSITIVE LOGITS
    åī¯å¸Ĥéķ¿
    0.29
    çĶŁäºİ
    0.28
    /Runtime
    0.25
    èĬ±äºĨ
    0.25
     Sofa
    0.25
    zier
    0.25
    çį¾
    0.25
    éŨåīį
    0.25
    .ordinal
    0.24
    ç´¢èµĶ
    0.24
    Activations Density 0.935%

    No Known Activations