© 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. 25-TRANSCODER-HP
    7. 107871
    Prev
    Next
    INDEX
    Explanations

    websites and applications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ermen
    -0.31
    atis
    -0.28
    å°Ķ
    -0.27
    annonce
    -0.27
    mania
    -0.26
    benh
    -0.25
    ervative
    -0.24
    RITE
    -0.24
    ESÄ°
    -0.24
    yd
    -0.24
    POSITIVE LOGITS
    .unregister
    0.30
    åħ³åı£
    0.29
    大éĺŁ
    0.27
    liness
    0.26
    对æĸ¹
    0.25
    /un
    0.25
    شد
    0.25
    æĮª
    0.24
    æľµ
    0.24
    links
    0.24
    Activations Density 0.921%

    No Known Activations