© 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. 31-TRANSCODER-HP
    7. 18355
    Prev
    Next
    INDEX
    Explanations

    state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vrier
    -0.27
    æ¹Ħ
    -0.21
    èį»
    -0.21
    æ¿ij
    -0.21
    å½ĵä¹ĭæĹłæĦ§
    -0.21
    ËIJ
    -0.21
    åĪį
    -0.20
    伯
    -0.20
     обÑĢаÑīа
    -0.20
    æĭ¥æĬ¤
    -0.20
    POSITIVE LOGITS
     state
    1.95
    çĬ¶æĢģ
    1.88
    state
    1.73
     states
    1.70
    -state
    1.63
    çļĦçĬ¶æĢģ
    1.62
     State
    1.57
    çĭĢæħĭ
    1.53
    State
    1.49
    _state
    1.48
    Activations Density 22.103%

    No Known Activations