Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 61914
    Prev
    Next
    INDEX
    Explanations

    canal

    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
     getP
    -0.08
    .gson
    -0.08
     Northwestern
    -0.07
     assh
    -0.07
     Guill
    -0.07
    各个
    -0.07
    규
    -0.07
    轴承
    -0.06
     THAN
    -0.06
    这三个
    -0.06
    POSITIVE LOGITS
     canal
    0.09
     Canal
    0.08
    -a
    0.08
    dal
    0.07
    ᐉ
    0.07
    帶
    0.07
    獭
    0.07
    מסעד
    0.07
    剁
    0.07
    DV
    0.07
    Activations Density 0.003%

    No Known Activations