© 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. 18693
    Prev
    Next
    INDEX
    Explanations

    water and code

    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
    nı
    -0.28
    ArrayType
    -0.27
    èijµ
    -0.27
    mdl
    -0.25
    sites
    -0.25
    大åѦ
    -0.25
    å¹³åİŁ
    -0.25
     sites
    -0.25
    éĮĦ
    -0.24
    ding
    -0.24
    POSITIVE LOGITS
     familiar
    0.30
     cum
    0.29
    invert
    0.27
    åı¯è¡Į
    0.26
    lice
    0.26
    åĪ»
    0.25
    çĨŁæĤīçļĦ
    0.25
    intel
    0.25
     Loose
    0.24
     Fam
    0.24
    Activations Density 0.160%

    No Known Activations