© 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. 53367
    Prev
    Next
    INDEX
    Explanations

    r

    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
     stand
    -0.41
     standing
    -0.40
     Stand
    -0.38
     Standing
    -0.38
    standing
    -0.34
    Standing
    -0.34
    _stand
    -0.34
    Stand
    -0.33
    stand
    -0.31
     stands
    -0.31
    POSITIVE LOGITS
    ipc
    0.28
    æ¦Ķ
    0.25
    Fun
    0.25
    æĢĢ
    0.25
    _fun
    0.24
    bet
    0.24
    phem
    0.24
     cheesy
    0.24
    骡
    0.24
     playable
    0.24
    Activations Density 0.011%

    No Known Activations