© 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. 54119
    Prev
    Next
    INDEX
    Explanations

    rotating mechanical parts

    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
    cis
    -0.27
    r
    -0.26
     Retrie
    -0.26
     hyp
    -0.25
    acket
    -0.24
     Hyp
    -0.24
     concentrated
    -0.23
    hyp
    -0.23
     Harper
    -0.23
    ãģĹãģ¾
    -0.23
    POSITIVE LOGITS
    -round
    0.33
    -hand
    0.29
    -life
    0.27
    -cluster
    0.27
    -serving
    0.26
    -party
    0.26
    éĦĦ
    0.26
    -direction
    0.26
    omer
    0.26
    -service
    0.26
    Activations Density 0.038%

    No Known Activations