© 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. 24-TRANSCODER-HP
    7. 149978
    Prev
    Next
    INDEX
    Explanations

    relationships and associations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ican
    -0.28
     unlikely
    -0.26
    ÑĤÑĢо
    -0.25
    ãģ»ãģ¼
    -0.25
    ahoma
    -0.24
     external
    -0.24
    \Queue
    -0.24
    éĦł
    -0.24
     Hercules
    -0.24
    .hy
    -0.23
    POSITIVE LOGITS
    upert
    0.31
     associations
    0.30
    membership
    0.30
     relationship
    0.29
     counts
    0.29
     relation
    0.29
    Relation
    0.28
     association
    0.28
    Relationship
    0.28
    åħ³ç³»
    0.28
    Activations Density 0.304%

    No Known Activations