© 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. 77384
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     incident
    -0.08
    isti
    -0.07
     invested
    -0.07
     occurs
    -0.06
    祭
    -0.06
     found
    -0.06
    taken
    -0.06
     extension
    -0.06
     didSelectRowAtIndexPath
    -0.06
    ились
    -0.06
    POSITIVE LOGITS
     Сам
    0.08
     loung
    0.07
    ]bool
    0.07
    되었다
    0.07
     Horn
    0.07
     counselors
    0.07
     сериал
    0.07
     aes
    0.07
    _unicode
    0.07
    VALUES
    0.07
    Activations Density 0.201%

    No Known Activations