© 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. 163135
    Prev
    Next
    INDEX
    Explanations

    Acceptability

    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
    inspace
    -0.33
    Sites
    -0.28
    sites
    -0.28
    åįģä¸ī
    -0.27
    belief
    -0.26
    itives
    -0.26
    åĿļæĮģ以
    -0.25
    áĥķ
    -0.25
     belief
    -0.24
     sightings
    -0.24
    POSITIVE LOGITS
    plemented
    0.28
    _MATCH
    0.26
    ewise
    0.26
    ä»Ĭãģ¯
    0.25
    ç½Ķ
    0.25
    決ãĤģ
    0.25
    Match
    0.24
    éĶĻäºĨ
    0.24
    ção
    0.23
    æ¯ĶèµĽä¸Ń
    0.23
    Activations Density 0.010%

    No Known Activations