© 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. 22-TRANSCODER-HP
    7. 97751
    Prev
    Next
    INDEX
    Explanations

    Crit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aims
    -0.29
    éģĵ路交éĢļ
    -0.28
     earthly
    -0.27
    umann
    -0.26
    å¤ĸçķĮ
    -0.26
    ToOne
    -0.25
    åħ¨æĹ¥åĪ¶
    -0.25
    ongs
    -0.25
    inations
    -0.25
    guarded
    -0.25
    POSITIVE LOGITS
     Charter
    0.27
     âĺ
    0.26
     Ob
    0.25
    Tro
    0.25
     setw
    0.25
    QUI
    0.25
     æŀ
    0.25
     pl
    0.25
     pledge
    0.24
     bu
    0.24
    Activations Density 0.002%

    No Known Activations