© 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. 30-TRANSCODER-HP
    7. 95453
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯ĹæŃĮ
    -0.66
    è¯Ĺ
    -0.66
     poem
    -0.65
    po
    -0.59
    è©©
    -0.59
     poems
    -0.59
    (po
    -0.58
     poetic
    -0.58
     poetry
    -0.58
     po
    -0.56
    POSITIVE LOGITS
    æ³ķå®Ŀ
    0.28
    çĴł
    0.26
     BIN
    0.26
    flies
    0.26
    ãĥĶãĥ³
    0.25
     rotate
    0.24
    éĢł
    0.24
    æĿijéķĩ
    0.24
    ãĤŃãĥ£ãĥ©
    0.24
    鸷
    0.23
    Activations Density 0.882%

    No Known Activations