© 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. 41546
    Prev
    Next
    INDEX
    Explanations

    code/legal text

    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
    /interface
    -0.31
    fa
    -0.26
    çĶ¸
    -0.25
    èĦī
    -0.25
    åĮħè£ħ
    -0.25
    unnel
    -0.25
     fa
    -0.24
    faf
    -0.24
    xp
    -0.24
    ê³¼ìłķ
    -0.24
    POSITIVE LOGITS
    .Disclaimer
    0.30
    éĽħ
    0.30
    åįģåĪĨéĴŁ
    0.26
     Incorporated
    0.25
     ACS
    0.25
    æīĵãģ¡
    0.24
    isci
    0.24
    odia
    0.24
    incer
    0.24
     conting
    0.23
    Activations Density 0.001%

    No Known Activations