© 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. 32-TRANSCODER-HP
    7. 41933
    Prev
    Next
    INDEX
    Explanations

    technical/weapon specifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çħ
    -0.27
    bens
    -0.26
    IVED
    -0.26
    ghost
    -0.25
    è§Ħ
    -0.25
    SEE
    -0.25
     occ
    -0.25
    Refs
    -0.25
     Tap
    -0.24
     pancre
    -0.24
    POSITIVE LOGITS
    longleftrightarrow
    0.28
    tu
    0.26
     digs
    0.25
    obbies
    0.25
    ')</
    0.24
    篦
    0.24
    ä»ħ次äºİ
    0.24
    ãĥĩãĤ£ãĥ³ãĤ°
    0.24
    ä¼Ĺ
    0.24
     pitches
    0.24
    Activations Density 0.000%

    No Known Activations