© 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. 96161
    Prev
    Next
    INDEX
    Explanations

    It

    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
    caret
    -0.26
     care
    -0.25
     Bris
    -0.24
     Glas
    -0.24
    严
    -0.24
     Wet
    -0.24
     disclosing
    -0.24
    æĥ³åĪ°äºĨ
    -0.23
     Random
    -0.23
     randomness
    -0.23
    POSITIVE LOGITS
    ”↵
    0.40
    licas
    0.29
    no
    0.29
    ”
    0.28
    ’all
    0.28
     all
    0.28
     no
    0.28
    ”;
    0.28
    ”↵↵
    0.27
    .”↵
    0.27
    Activations Density 0.108%

    No Known Activations