© 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. 53504
    Prev
    Next
    INDEX
    Explanations

    code, XML, and technical docs

    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
     lu
    -0.28
     Sm
    -0.27
    ir
    -0.27
    iro
    -0.27
    IRO
    -0.27
     pap
    -0.26
     cables
    -0.26
     Earth
    -0.26
    iros
    -0.26
    ires
    -0.25
    POSITIVE LOGITS
    ustum
    0.31
    yme
    0.30
    ymes
    0.29
    æĺĻ
    0.28
    fluence
    0.28
    ymi
    0.27
    articles
    0.26
    éĺ±
    0.25
     Bd
    0.25
    çĶ²çĬ¶
    0.24
    Activations Density 0.007%

    No Known Activations