© 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. 42665
    Prev
    Next
    INDEX
    Explanations

    News reports

    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
    LEX
    -0.29
    åıijå±ķè§ĦåĪĴ
    -0.27
    atsu
    -0.25
    ever
    -0.25
    å¼ĺæī¬
    -0.24
    force
    -0.24
     impuls
    -0.24
    亵
    -0.23
    ENA
    -0.23
    ×ij×¢
    -0.23
    POSITIVE LOGITS
     Fall
    0.28
    undance
    0.28
    Fall
    0.27
     Condition
    0.27
    oba
    0.27
    .ease
    0.26
     Pret
    0.25
    agedList
    0.25
     Conditions
    0.25
     Gr
    0.25
    Activations Density 0.008%

    No Known Activations