© 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. 107953
    Prev
    Next
    INDEX
    Explanations

    Gram

    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
     tome
    -0.29
     vict
    -0.27
     tact
    -0.27
    ç´ļ
    -0.27
    è¡Ķ
    -0.26
     crush
    -0.26
    RYPTO
    -0.25
    ãģĵãģĿ
    -0.25
    łģ
    -0.24
     MSR
    -0.24
    POSITIVE LOGITS
    er
    0.34
    erate
    0.31
    å¤Ł
    0.27
    alus
    0.27
     deputies
    0.26
    æıŃ示
    0.26
    y
    0.25
    ró
    0.25
    åŃIJ
    0.25
    ccoli
    0.25
    Activations Density 0.077%

    No Known Activations