© 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. 87777
    Prev
    Next
    INDEX
    Explanations

    people

    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
     Men
    -0.28
    zac
    -0.26
    .US
    -0.25
    主åĬŀ
    -0.25
    uth
    -0.24
    _Row
    -0.24
    éĢĶ
    -0.24
     Harper
    -0.24
    ä¹Ŀ大
    -0.23
     men
    -0.23
    POSITIVE LOGITS
    umpt
    0.29
    scape
    0.27
    vents
    0.27
    spacer
    0.26
    segments
    0.26
     scape
    0.25
    åħįéĻ¤
    0.25
     Duc
    0.24
    riter
    0.24
    ht
    0.24
    Activations Density 0.017%

    No Known Activations