© 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. 42505
    Prev
    Next
    INDEX
    Explanations

    chemistry/scientific data

    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
     Eli
    -0.26
     cil
    -0.26
    Procedure
    -0.26
    iner
    -0.26
     hal
    -0.26
    HEEL
    -0.25
     disproportion
    -0.25
    deer
    -0.25
    çĨĦ
    -0.24
    åģ¶
    -0.24
    POSITIVE LOGITS
    plib
    0.29
    TeX
    0.28
     tek
    0.26
    èĩªçĦ¶èĢĮ
    0.25
    emens
    0.25
    è´¨éĩıåĴĮ
    0.25
    valueOf
    0.24
    (equal
    0.24
    lete
    0.24
    为大家
    0.24
    Activations Density 0.004%

    No Known Activations