© 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. 98762
    Prev
    Next
    INDEX
    Explanations

    in

    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
    hic
    -0.30
    èĬĥ
    -0.25
    oman
    -0.24
     present
    -0.24
    ])]
    -0.24
     tended
    -0.24
    elan
    -0.24
    å¤ĦåĪĨ
    -0.24
    present
    -0.23
    èĵĭ
    -0.23
    POSITIVE LOGITS
     prior
    0.33
     ÑĢанее
    0.26
     Prior
    0.26
     ,
    0.25
    深深çļĦ
    0.25
    rior
    0.24
    Prior
    0.24
    .redis
    0.24
    ило
    0.24
     priorit
    0.24
    Activations Density 0.006%

    No Known Activations