© 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. 1950
    Prev
    Next
    INDEX
    Explanations

    yaml

    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
    �断
    -0.08
    evento
    -0.08
     True
    -0.07
     distance
    -0.07
     re
    -0.07
     true
    -0.07
     конструкци
    -0.07
     incentive
    -0.07
     얘
    -0.07
    创新发展
    -0.07
    POSITIVE LOGITS
     cortical
    0.08
     pitcher
    0.07
     staining
    0.07
     Criterion
    0.07
    ────
    0.07
    萹
    0.07
    ܒ
    0.07
     installations
    0.07
     Drill
    0.07
    ERGY
    0.07
    Activations Density 0.002%

    No Known Activations