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. 15-RESID-POST-AA
    6. 127929
    Prev
    Next
    INDEX
    Explanations

    Parliament

    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
    ulerAngles
    -0.07
    牢牢
    -0.07
    共同
    -0.07
     Summit
    -0.07
    刑事案件
    -0.06
     surrender
    -0.06
    ognito
    -0.06
    unteer
    -0.06
     matches
    -0.06
     cheer
    -0.06
    POSITIVE LOGITS
    谱
    0.07
     INTERFACE
    0.07
    𝑵
    0.07
    .Br
    0.07
     objections
    0.07
     nặng
    0.07
     gleich
    0.06
    กร
    0.06
     الك
    0.06
    Ꭿ
    0.06
    Activations Density 0.006%

    No Known Activations