© 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. 25-TRANSCODER-HP
    7. 107906
    Prev
    Next
    INDEX
    Explanations

    say the ending "-asis/-atic"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃķ
    -0.31
    å·²ä¹ħ
    -0.27
    udas
    -0.26
    alore
    -0.26
    åľ°ä¸Ń
    -0.26
     Poll
    -0.26
    æĹ¥åīį
    -0.25
    æĢİä¹Ī说
    -0.24
    æijŀ
    -0.24
     Pers
    -0.24
    POSITIVE LOGITS
    ensors
    0.29
    æ¶ī
    0.27
    eners
    0.27
     mechan
    0.26
    éªĭ
    0.25
    iance
    0.25
     state
    0.25
    çĬ¶åĨµ
    0.24
    rian
    0.23
    .currentState
    0.23
    Activations Density 1.084%

    No Known Activations