© 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. 35-TRANSCODER-HP
    7. 39466
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ous
    -0.28
     prefer
    -0.28
    ä¾Ŀçħ§
    -0.28
    StreamReader
    -0.25
    usu
    -0.24
     trom
    -0.24
    atal
    -0.24
     dependency
    -0.24
    è·Łéļı
    -0.24
     Vers
    -0.24
    POSITIVE LOGITS
    ab
    0.40
     ab
    0.40
    -ab
    0.38
    AB
    0.35
    abe
    0.35
     AB
    0.34
    _ab
    0.34
    (ab
    0.33
     Ab
    0.33
    Ab
    0.32
    Activations Density 0.043%

    No Known Activations