© 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. 32-TRANSCODER-HP
    7. 43484
    Prev
    Next
    INDEX
    Explanations

    web context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħī
    -0.82
    åįķ
    -0.48
    single
    -0.42
     single
    -0.40
    (single
    -0.38
     light
    -0.36
    åħīçħ§
    -0.35
    Single
    -0.35
    åħīæºIJ
    -0.34
    åħīçĶµ
    -0.34
    POSITIVE LOGITS
     web
    0.31
    web
    0.30
    Web
    0.30
     getContext
    0.29
    _web
    0.28
     Web
    0.28
     Context
    0.28
    ctx
    0.27
    _context
    0.26
    CTX
    0.26
    Activations Density 0.075%

    No Known Activations