© 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. 54216
    Prev
    Next
    INDEX
    Explanations

    Technical texts

    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
    icken
    -0.28
     bin
    -0.28
    åĽĽä½į
    -0.26
     narrowing
    -0.26
     sur
    -0.26
     l
    -0.26
    åĬ¨åĬĽ
    -0.26
    èĹī
    -0.25
     br
    -0.25
    osi
    -0.25
    POSITIVE LOGITS
    ipl
    0.27
    theon
    0.26
     Uph
    0.26
    Them
    0.25
    汤
    0.24
    æĬĬå®ĥ
    0.24
     splitted
    0.24
    è´¢
    0.24
    åıĭè°Ĭ
    0.24
     uploader
    0.24
    Activations Density 0.011%

    No Known Activations