© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107012
    Prev
    Next
    INDEX
    Explanations

    ag

    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
    Negative Logits
    带åĬ¨
    -0.29
     converged
    -0.26
     Consolid
    -0.25
     rel
    -0.25
     union
    -0.25
    imiter
    -0.24
    :nth
    -0.24
    orman
    -0.24
     ev
    -0.24
     consolidation
    -0.24
    POSITIVE LOGITS
    bed
    0.29
    èļ±
    0.27
    å¤ļä½ĻçļĦ
    0.26
    proof
    0.26
    çĸĸ
    0.25
    eneg
    0.25
    äºĮèĢħ
    0.24
    _special
    0.24
     proof
    0.23
    Special
    0.23
    Activations Density 0.052%

    No Known Activations