© 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. 23-TRANSCODER-HP
    7. 24807
    Prev
    Next
    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specifications
    -0.28
     specification
    -0.27
    äºĨäºĽ
    -0.25
    ONSE
    -0.25
     slightest
    -0.25
    累累
    -0.24
    Specification
    -0.24
    äºĨä»ĸçļĦ
    -0.24
     metals
    -0.23
    itals
    -0.23
    POSITIVE LOGITS
    ht
    0.27
    pherical
    0.26
    arius
    0.26
    iren
    0.26
    ingular
    0.25
    jour
    0.24
    æľ«
    0.24
    éĹ»
    0.24
    端
    0.23
    åıijæĮ¥
    0.23
    Activations Density 1.079%

    No Known Activations