© 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. 53701
    Prev
    Next
    INDEX
    Explanations

    Discussing issues

    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
     blocks
    -0.34
    blocks
    -0.30
    åĿĹ
    -0.30
    (blocks
    -0.29
     Blocks
    -0.29
    	Block
    -0.29
    loh
    -0.28
    ])*
    -0.28
    .blocks
    -0.27
    Blocks
    -0.27
    POSITIVE LOGITS
     resulting
    0.28
     effect
    0.27
     sidel
    0.27
    å±ģèĤ¡
    0.27
    æ¯ķ
    0.26
     hind
    0.26
     effects
    0.25
     hep
    0.25
    untlet
    0.25
    ’h
    0.24
    Activations Density 0.026%

    No Known Activations