© 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. 54257
    Prev
    Next
    INDEX
    Explanations

    Code and licensing context

    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
    liche
    -0.27
    ow
    -0.26
    ropdown
    -0.24
    them
    -0.24
    _predicted
    -0.24
    Existing
    -0.24
     rz
    -0.24
    naz
    -0.23
    akk
    -0.23
    rich
    -0.23
    POSITIVE LOGITS
     Fee
    0.28
    åĨįä¹Łä¸į
    0.28
    é¦ħ
    0.26
     unread
    0.25
    หา
    0.24
    éģ½
    0.24
    åŁİéĩĮ
    0.24
    èĤĺ
    0.23
    两岸
    0.23
    樾
    0.23
    Activations Density 0.027%

    No Known Activations