© 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. 25-TRANSCODER-HP
    7. 107836
    Prev
    Next
    INDEX
    Explanations

    Coding and file information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĺĬ
    -0.26
    èĭĶ
    -0.26
    aksi
    -0.26
    fcn
    -0.26
    åħ·ä½ĵåĨħ容
    -0.25
     prominently
    -0.25
     Implemented
    -0.25
    鹫
    -0.25
    æľĢå¤ļ
    -0.24
    itti
    -0.24
    POSITIVE LOGITS
     ours
    0.32
    çĶ¨å¾®ä¿¡
    0.28
     my
    0.28
     our
    0.27
     mine
    0.27
    Ïİ
    0.25
     Warren
    0.25
    æĪijçļĦ
    0.25
     mec
    0.25
    æĪij们çļĦ
    0.24
    Activations Density 0.989%

    No Known Activations