© 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. 88417
    Prev
    Next
    INDEX
    Explanations

    Dates

    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
    æģ¹
    -0.29
    èĵĿåĽ¾
    -0.25
    acles
    -0.25
    itution
    -0.24
    andler
    -0.24
    .struct
    -0.24
    stringstream
    -0.24
    acle
    -0.24
     chamber
    -0.24
    _CLUSTER
    -0.24
    POSITIVE LOGITS
    ·
    0.30
    æł¸å¿ĥåĮº
    0.27
    æł¸
    0.27
    Jo
    0.26
    åĬŀ
    0.26
     RID
    0.25
    ä¹ĭäºĭ
    0.25
    oda
    0.25
    缮
    0.24
    çijŀ
    0.24
    Activations Density 0.020%

    No Known Activations