© 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. 9130
    Prev
    Next
    INDEX
    Explanations

    say "true"

    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
     IST
    -0.26
    åľ¨æĪij
    -0.24
    ocab
    -0.24
    æıIJåĩºçļĦ
    -0.23
     comprom
    -0.23
    RAFT
    -0.23
    .Rem
    -0.23
    (parameter
    -0.23
    -anchor
    -0.23
    -Cs
    -0.23
    POSITIVE LOGITS
    çĶ²
    0.27
    orado
    0.26
    annis
    0.26
    hp
    0.26
    è¿ĽåĨĽ
    0.25
    æĸij
    0.25
    iad
    0.24
    æĪĬ
    0.24
    纯粹
    0.24
    pool
    0.24
    Activations Density 0.003%

    No Known Activations