© 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. 57173
    Prev
    Next
    INDEX
    Explanations

    diving/delving into something

    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
    rich
    -0.29
    ablish
    -0.27
    Õµ
    -0.25
     deduction
    -0.25
    caf
    -0.25
    ativa
    -0.24
    je
    -0.24
    reeNode
    -0.24
    rophe
    -0.24
    ital
    -0.23
    POSITIVE LOGITS
     recip
    0.27
    psilon
    0.27
    into
    0.27
    icorn
    0.26
     into
    0.26
    heet
    0.24
    宽
    0.24
    ·¨
    0.24
    osterone
    0.24
     deeply
    0.23
    Activations Density 0.789%

    No Known Activations