© 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. 97729
    Prev
    Next
    INDEX
    Explanations

    't

    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
    xFB
    -0.26
    Pokemon
    -0.25
    antry
    -0.24
    æľī幸
    -0.24
    cÃŃ
    -0.24
    mojom
    -0.24
    idl
    -0.24
    赶åĪ°
    -0.24
    .Factory
    -0.24
    ges
    -0.24
    POSITIVE LOGITS
     Russians
    0.28
     Russian
    0.28
    alie
    0.27
    -life
    0.27
    åij½
    0.27
     rabbit
    0.26
     Moscow
    0.26
    zÄĻ
    0.25
    aylor
    0.25
    sink
    0.24
    Activations Density 0.018%

    No Known Activations