© 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. 2335
    Prev
    Next
    INDEX
    Explanations

    plant hardiness zones

    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
    预防
    -0.07
    Office
    -0.07
     Fletcher
    -0.07
    Users
    -0.07
    运输
    -0.07
    电器
    -0.07
     ComboBox
    -0.06
    发
    -0.06
     Office
    -0.06
    嗓子
    -0.06
    POSITIVE LOGITS
    (candidate
    0.08
    แหละ
    0.08
     (~
    0.07
     Shane
    0.07
     Megan
    0.07
     declares
    0.07
    nesc
    0.07
    ...",
    0.07
    ashington
    0.07
     Placeholder
    0.07
    Activations Density 0.020%

    No Known Activations