© 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. 33-TRANSCODER-HP
    7. 53668
    Prev
    Next
    INDEX
    Explanations

    US government agencies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĩ¥
    -0.29
     Episcopal
    -0.25
    dig
    -0.24
    åĵĢ
    -0.24
     REFER
    -0.24
    èĪ¹
    -0.24
     EntityType
    -0.24
    âģ¿
    -0.24
    .Pointer
    -0.23
    .ship
    -0.23
    POSITIVE LOGITS
    çľĭçĶµè§Ĩ
    0.29
    aly
    0.28
    De
    0.28
     de
    0.26
     De
    0.26
     watches
    0.26
    USA
    0.24
    .palette
    0.24
    _de
    0.24
    phony
    0.24
    Activations Density 0.039%

    No Known Activations