© 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. 108189
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ç¼Ģ
    -0.26
    髦
    -0.25
     conj
    -0.24
     weighing
    -0.24
     symbolic
    -0.24
     Minor
    -0.23
     Firstly
    -0.23
    èĭĩ
    -0.23
    SHOT
    -0.23
     minor
    -0.23
    POSITIVE LOGITS
    ä¸įå¤Ł
    0.28
    avenport
    0.26
    è´§
    0.25
    jah
    0.25
    æĬĵä½ı
    0.24
    RIX
    0.24
    满æĢĢ
    0.24
    çĽİ
    0.23
     draped
    0.23
    æİīäºĨ
    0.23
    Activations Density 0.900%

    No Known Activations