© 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. 35-TRANSCODER-HP
    7. 39261
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıijçĶŁçļĦ
    -0.29
    URY
    -0.27
    çĦĺ
    -0.26
     MyBase
    -0.26
     nIndex
    -0.26
     IsNot
    -0.25
    çŀ
    -0.25
    çļĦåıijçĶŁ
    -0.24
    -mm
    -0.24
    IMS
    -0.24
    POSITIVE LOGITS
    书æ³ķ家
    0.26
    çł´
    0.26
    éģĵ士
    0.26
     dryer
    0.26
    åĬ¨ä½ľ
    0.25
    âĹĦ
    0.25
    ither
    0.25
     dark
    0.24
    quir
    0.24
    åħįè´£
    0.24
    Activations Density 51.707%

    No Known Activations

    This feature has no known activations.