© 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. 95790
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
     twist
    -0.27
    )arg
    -0.26
    åİŁä»¶
    -0.24
    å¹²åĩĢ
    -0.24
    _drvdata
    -0.24
     prominently
    -0.24
    ][:
    -0.23
    parable
    -0.23
    ardin
    -0.23
    =\"#
    -0.23
    POSITIVE LOGITS
    ions
    0.36
    IONS
    0.30
    ers
    0.28
    yers
    0.27
    EC
    0.27
    ech
    0.27
    ION
    0.27
    ional
    0.27
    ãģ³
    0.27
    undra
    0.26
    Activations Density 0.018%

    No Known Activations