© 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. 15-RESID-POST-AA
    11. 48865
    Prev
    Next
    INDEX
    Explanations

    bile

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bears
    -0.07
     wo
    -0.07
    inea
    -0.07
    _box
    -0.07
    בעלי
    -0.07
     Guinea
    -0.07
     salario
    -0.07
    trfs
    -0.07
    ካ
    -0.07
    .dequeue
    -0.07
    POSITIVE LOGITS
     WL
    0.08
    big
    0.07
    っぽ
    0.07
    ()->
    0.07
     defenders
    0.07
     Jad
    0.06
     motivation
    0.06
    athlete
    0.06
    绑
    0.06
    -ap
    0.06
    Activations Density 0.066%

    No Known Activations