© 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. 22669
    Prev
    Next
    INDEX
    Explanations

    Technical/Informational documents

    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
    ໄ
    -0.07
    	resp
    -0.06
     ев
    -0.06
    resume
    -0.06
     JV
    -0.06
    .shape
    -0.06
     Mutual
    -0.06
    /mat
    -0.06
     drew
    -0.06
    /slider
    -0.06
    POSITIVE LOGITS
    架
    0.07
    ']").
    0.07
    ong
    0.07
    Ớ
    0.07
    ()<<"
    0.07
    먹
    0.06
    𝖉
    0.06
     znalaz
    0.06
    ☠
    0.06
    الم
    0.06
    Activations Density 0.921%

    No Known Activations