© 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. 96160
    Prev
    Next
    INDEX
    Explanations

    Mixed contexts

    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
     chem
    -0.27
    ILITY
    -0.27
    èŁ²
    -0.27
    NOWLED
    -0.26
    åĬŀ
    -0.25
    alu
    -0.24
     packed
    -0.24
    åºķéĥ¨
    -0.24
     tents
    -0.24
    imuth
    -0.23
    POSITIVE LOGITS
    å¹²
    0.29
    cop
    0.27
    estr
    0.27
     prosec
    0.27
     Stanley
    0.26
    _serializer
    0.26
    å¿ĥåĬ¨
    0.26
     dry
    0.26
     cou
    0.25
    degrees
    0.25
    Activations Density 0.000%

    No Known Activations