© 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. 25-TRANSCODER-HP
    7. 109171
    Prev
    Next
    INDEX
    Explanations

    Ay

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    czy
    -0.28
    uppet
    -0.26
    าะ
    -0.26
    esub
    -0.26
    extra
    -0.26
     chẳng
    -0.25
    æłħ
    -0.24
    input
    -0.24
     reverse
    -0.24
    gin
    -0.24
    POSITIVE LOGITS
    urved
    0.29
    èĥļ
    0.25
    zel
    0.25
    (acc
    0.25
     phy
    0.24
    leys
    0.24
    ngen
    0.24
    å³Ĵ
    0.24
    neighbors
    0.24
    .syntax
    0.24
    Activations Density 1.092%

    No Known Activations