© 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. 30-TRANSCODER-HP
    7. 95288
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    's
    -0.26
     اÙĦÙħصدر
    -0.25
    ude
    -0.24
    è°§
    -0.24
    çļĦå°±æĺ¯
    -0.24
    äºĴéĢļ
    -0.24
    -'
    -0.24
    -
    -0.23
    ’s
    -0.23
     listened
    -0.23
    POSITIVE LOGITS
    ropa
    0.28
    举
    0.26
    è¾¹
    0.26
    躺
    0.26
    avior
    0.25
     carr
    0.25
    çĮİ
    0.25
    ÑĥеÑĤÑģÑı
    0.25
    ?,?,?,?,
    0.25
    è´¥
    0.24
    Activations Density 0.053%

    No Known Activations