© 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. 32-TRANSCODER-HP
    7. 42106
    Prev
    Next
    INDEX
    Explanations

    Incomplete sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ega
    -0.25
    inge
    -0.24
    ether
    -0.24
    åĽ½äºº
    -0.24
    erness
    -0.24
    FieldType
    -0.23
    èľķ
    -0.23
    ocking
    -0.23
    Argb
    -0.23
    boards
    -0.23
    POSITIVE LOGITS
     abstract
    0.29
    ús
    0.28
     aff
    0.27
    usp
    0.27
    ú
    0.27
    furt
    0.26
    P
    0.25
     uur
    0.24
    UV
    0.24
    åľ©
    0.24
    Activations Density 0.001%

    No Known Activations