© 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
    2. Qwen3-4B
    3. 33-TRANSCODER-HP
    4. 54012
    Prev
    Next
    INDEX
    Explanations

    non-English

    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
    Frameworks
    -0.30
    opus
    -0.28
     seeding
    -0.26
    emo
    -0.26
    etest
    -0.24
    éĻĤ
    -0.24
    dm
    -0.24
     forgive
    -0.23
    Bi
    -0.23
    inous
    -0.23
    POSITIVE LOGITS
    åľ¨äºİ
    0.28
    åľ£
    0.26
    ừa
    0.24
    èı²
    0.24
    头éĥ¨
    0.24
    ÑĦик
    0.24
    .cert
    0.24
    -ST
    0.23
     anchor
    0.23
    建议
    0.23
    Activations Density 0.024%

    No Known Activations