© 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. 95807
    Prev
    Next
    INDEX
    Explanations

    Code or licensing-related 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
    blas
    -0.28
    èµ·
    -0.25
    ([^
    -0.24
    cars
    -0.24
    chai
    -0.24
     vetor
    -0.23
    åĩºè®©
    -0.23
    خصص
    -0.23
    getFile
    -0.23
    -vars
    -0.23
    POSITIVE LOGITS
    grading
    0.29
    нÑı
    0.26
     Or
    0.26
     armed
    0.25
    emos
    0.25
     Bon
    0.24
    翼
    0.24
     MS
    0.23
    inn
    0.23
     Workflow
    0.23
    Activations Density 0.101%

    No Known Activations