© 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. 12-TRANSCODER-HP
    7. 22707
    Prev
    Next
    INDEX
    Explanations

    Watch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mate
    -0.27
    èĬĿ
    -0.26
    urst
    -0.26
    为æĤ¨
    -0.26
     craft
    -0.26
     static
    -0.25
    人éĢī
    -0.25
     followed
    -0.24
     comple
    -0.24
    secutive
    -0.24
    POSITIVE LOGITS
    endon
    0.28
    çļĦéģĵçIJĨ
    0.26
     Mosul
    0.25
    çĭ±
    0.25
    ÅĤat
    0.25
    管éģĵ
    0.25
    饱满
    0.24
    å¾ģ
    0.24
     motive
    0.24
    èĪĤ
    0.24
    Activations Density 0.000%

    No Known Activations