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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162524
    Prev
    Next
    INDEX
    Explanations

    0

    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
    REFERENCES
    -0.26
    å¤ĩçĶ¨
    -0.26
    enser
    -0.23
    amon
    -0.23
    ashes
    -0.23
    (Pointer
    -0.22
    .Character
    -0.22
     Son
    -0.22
    ész
    -0.22
    å°Ĩ以
    -0.22
    POSITIVE LOGITS
    ophobic
    0.26
    -inverse
    0.25
    ergy
    0.25
    icro
    0.25
    å°¼äºļ
    0.24
    åīįæīĢ
    0.24
    irk
    0.24
    Opp
    0.23
     kinetics
    0.23
     marsh
    0.23
    Activations Density 0.184%

    No Known Activations