© 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. 96246
    Prev
    Next
    INDEX
    Explanations

    Unusual text

    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
    rift
    -0.31
    ankan
    -0.29
     moments
    -0.28
    emia
    -0.27
    abei
    -0.27
    lat
    -0.26
     niên
    -0.25
    éł
    -0.25
     Prop
    -0.25
     penetrating
    -0.25
    POSITIVE LOGITS
    uele
    0.28
    æijĦåħ¥
    0.26
     ActiveForm
    0.26
    inc
    0.26
    ('('
    0.25
    uae
    0.25
    quals
    0.25
     spons
    0.24
     itemprop
    0.24
    quine
    0.24
    Activations Density 0.884%

    No Known Activations