© 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. 42558
    Prev
    Next
    INDEX
    Explanations

    specifications related words

    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
    äºijéĽĨ
    -0.27
    ÙĦÙĬÙĨ
    -0.26
    éĢıéľ²
    -0.26
    udu
    -0.25
    ilit
    -0.25
    arie
    -0.25
    aison
    -0.25
    atie
    -0.25
    itin
    -0.25
    åIJį家
    -0.24
    POSITIVE LOGITS
    æĮĩ
    1.20
    -spec
    0.72
     espec
    0.66
     spec
    0.66
     Spec
    0.62
    spec
    0.62
    _spec
    0.60
    Spec
    0.59
    	spec
    0.57
     SPEC
    0.57
    Activations Density 0.006%

    No Known Activations