© 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. 41780
    Prev
    Next
    INDEX
    Explanations

    Technical data/code

    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
     SIGNAL
    -0.26
    æĭī
    -0.26
    finity
    -0.25
    ecer
    -0.25
    ä¿¡
    -0.24
    Emer
    -0.24
    .Signal
    -0.24
    Signals
    -0.24
     coll
    -0.23
    æŶè£ħ
    -0.23
    POSITIVE LOGITS
    aki
    0.28
    pré
    0.28
    å°¼æĸ¯
    0.27
    åIJ¸æĶ¶
    0.26
    俳
    0.25
    Mas
    0.25
    åĮĻ
    0.25
     mas
    0.25
    æijĦ
    0.24
    opr
    0.24
    Activations Density 0.000%

    No Known Activations