© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 23314
    Prev
    Next
    INDEX
    Explanations

    Ch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ken
    -0.08
    悭
    -0.08
    试点
    -0.08
    ぬ
    -0.07
    ẩm
    -0.07
     Waterproof
    -0.07
    -for
    -0.07
    ToDo
    -0.07
     tội
    -0.07
    Ian
    -0.07
    POSITIVE LOGITS
     Ch
    0.08
     shrimp
    0.07
     primo
    0.07
     Jays
    0.07
    发电机
    0.07
     chord
    0.07
     fase
    0.07
    ﹼ
    0.07
     mux
    0.07
    חינ
    0.07
    Activations Density 0.036%

    No Known Activations