© 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. 163813
    Prev
    Next
    INDEX
    Explanations

    Legal/Scientific citations

    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
    anton
    -0.30
    usz
    -0.28
    atos
    -0.27
    inus
    -0.27
    ÅŃ
    -0.26
    czy
    -0.26
    åĨ¯
    -0.26
    queeze
    -0.26
    ovie
    -0.26
    ofil
    -0.25
    POSITIVE LOGITS
    esthesia
    0.26
     man
    0.26
    .assign
    0.25
    lycer
    0.24
    çĪ¸
    0.23
    legant
    0.23
    loth
    0.23
    驾çħ§
    0.23
    erase
    0.23
    erable
    0.23
    Activations Density 0.052%

    No Known Activations