© 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. 95318
    Prev
    Next
    INDEX
    Explanations

    model

    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
    å¼Ģçİ©ç¬ij
    -0.25
    纱
    -0.23
    ани
    -0.23
    iquer
    -0.23
    麻çĹ¹
    -0.23
    Å¡t
    -0.23
    ØŃاÙĨ
    -0.23
    ìĦŃ
    -0.22
    ή
    -0.22
    åĬŀ
    -0.22
    POSITIVE LOGITS
    模åŀĭ
    1.87
     model
    1.84
     models
    1.69
    model
    1.57
     Model
    1.52
    -model
    1.50
    ãĥ¢ãĥĩãĥ«
    1.48
    Model
    1.43
    _model
    1.42
     Models
    1.41
    Activations Density 2.697%

    No Known Activations