© 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. 53010
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
    well
    -0.34
    Well
    -0.31
     well
    -0.29
     Well
    -0.27
    áb
    -0.25
    abl
    -0.25
    çĶļèĩ³è¿ĺ
    -0.25
    Ñıвление
    -0.24
    èĥ½å¾ĹåĪ°
    -0.24
    ÃĵN
    -0.23
    POSITIVE LOGITS
    åİĦ
    0.30
     sn
    0.29
    éĶģå®ļ
    0.28
     pe
    0.28
     sw
    0.27
     c
    0.25
     sh
    0.25
    PE
    0.24
    داد
    0.24
    ettel
    0.24
    Activations Density 0.005%

    No Known Activations