© 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. 42906
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
     weight
    -0.28
    3
    -0.28
    _weight
    -0.27
    -weight
    -0.26
    .present
    -0.26
     WEIGHT
    -0.26
     Weight
    -0.26
    è¿ĩåİ»äºĨ
    -0.25
     grip
    -0.25
     weighted
    -0.25
    POSITIVE LOGITS
    çªģ
    0.32
    bite
    0.28
    _SOC
    0.28
     Blocks
    0.26
    CE
    0.25
    cion
    0.25
    cer
    0.25
    chains
    0.25
    Hall
    0.25
    nock
    0.25
    Activations Density 0.001%

    No Known Activations