© 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. 123657
    Prev
    Next
    INDEX
    Explanations

    run

    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
    韦
    -0.08
    เท
    -0.07
     minus
    -0.07
     File
    -0.07
     cz
    -0.07
     cor
    -0.07
    atum
    -0.07
    DED
    -0.07
    	done
    -0.07
    台湾
    -0.07
    POSITIVE LOGITS
     רבה
    0.08
    пром
    0.07
    Ⓝ
    0.07
    を作って
    0.07
    洗衣机
    0.07
    换届
    0.07
    🗓
    0.07
    쁨
    0.07
    pisa
    0.07
    -hole
    0.07
    Activations Density 0.001%

    No Known Activations