© 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. 87833
    Prev
    Next
    INDEX
    Explanations

    titles

    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
    _REASON
    -0.30
    aac
    -0.27
    è¸Ķ
    -0.26
    è¹Ī
    -0.26
    çļĦåŁºç¡Ģ
    -0.26
    ssize
    -0.24
    çļĦçIJĨçĶ±
    -0.24
    SEX
    -0.24
    er
    -0.23
     Kia
    -0.23
    POSITIVE LOGITS
    OfDay
    0.28
    æIJº
    0.27
    aleigh
    0.26
    Ĥæķ°
    0.25
    身份
    0.25
    åįıåĬŀ
    0.24
    æķıæĦŁ
    0.24
     Shirley
    0.24
    icable
    0.23
    aisy
    0.23
    Activations Density 0.041%

    No Known Activations