© 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. 31-TRANSCODER-HP
    7. 19572
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ho
    -0.31
     hang
    -0.28
    3
    -0.28
    2
    -0.28
    sw
    -0.27
    èIJ½
    -0.27
     ho
    -0.27
     generic
    -0.27
    ecd
    -0.27
    8
    -0.27
    POSITIVE LOGITS
    çĻ½éĵ¶
    0.31
    wich
    0.28
    ymoon
    0.27
    .buf
    0.27
    -binary
    0.27
    车ä¸Ĭ
    0.25
    CHEMY
    0.25
    éĶij
    0.25
    Animating
    0.25
    imson
    0.25
    Activations Density 7.692%

    No Known Activations