© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75230
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
    Nos
    -0.07
    OOM
    -0.07
     Gong
    -0.06
    elpers
    -0.06
    详情
    -0.06
     pepper
    -0.06
    욝
    -0.06
     Light
    -0.06
    ipers
    -0.06
    GLOSS
    -0.06
    POSITIVE LOGITS
    ◃
    0.07
     contracting
    0.07
    *A
    0.07
     Squad
    0.07
     tenant
    0.07
     badly
    0.07
     cặp
    0.06
    ")]
    ↵
    0.06
    ั
    0.06
    ToolStrip
    0.06
    Activations Density 0.109%

    No Known Activations