© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162999
    Prev
    Next
    INDEX
    Explanations

    allocate

    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
    éģ
    -0.29
    ä¸įåĪ°
    -0.27
    绥
    -0.26
    .safe
    -0.25
     franca
    -0.24
    plugin
    -0.24
    yet
    -0.23
    æ¯Ķä¸Ĭå¹´
    -0.23
    speaker
    -0.23
    ipel
    -0.22
    POSITIVE LOGITS
     allocation
    0.35
     assignments
    0.35
    åĪĨéħį
    0.34
     assignment
    0.33
    alloc
    0.31
     assigned
    0.30
    (assign
    0.29
     Assignment
    0.29
     assigns
    0.28
     alloc
    0.28
    Activations Density 0.066%

    No Known Activations