© 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. 54187
    Prev
    Next
    INDEX
    Explanations

    Orleans

    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
    incer
    -0.26
    rix
    -0.26
     Ox
    -0.26
    ulares
    -0.26
    plit
    -0.26
    æ¶Ī
    -0.25
     Grat
    -0.24
    å¸ĤæķĻèĤ²
    -0.24
    rike
    -0.24
    oyo
    -0.23
    POSITIVE LOGITS
    ga
    0.32
     ga
    0.27
     Kash
    0.26
    floating
    0.25
     stabbing
    0.25
    PM
    0.25
    Corner
    0.25
    KS
    0.24
    ASP
    0.24
     tentative
    0.24
    Activations Density 0.005%

    No Known Activations