© 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. 27-TRANSCODER-HP
    7. 57042
    Prev
    Next
    INDEX
    Explanations

    protect/preserve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»»ä½ķ人
    -0.30
    ä¼´
    -0.29
    ä»»ä½ķ人éĥ½
    -0.29
    éĢĤå½ĵ
    -0.27
    .aspect
    -0.25
     bÃłn
    -0.25
     Peninsula
    -0.25
     mess
    -0.24
     horizontally
    -0.24
    åı£å¾Ħ
    -0.24
    POSITIVE LOGITS
    å®Ŀè´µçļĦ
    0.33
    æ®ĸ
    0.32
    çıįè´µ
    0.29
    ayne
    0.29
     precious
    0.28
    æĸĩåĮĸéģĹ产
    0.28
    å®Ŀè´µ
    0.28
    çĶŁåij½
    0.27
    awe
    0.26
    çĶŁåij½çļĦ
    0.26
    Activations Density 0.004%

    No Known Activations