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. 23038
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    .setVisibility
    -0.07
    أفكار
    -0.07
    -notch
    -0.06
    管理部门
    -0.06
    Infinity
    -0.06
     vacation
    -0.06
    寝
    -0.06
    くなって
    -0.06
    を見
    -0.06
     Inspection
    -0.06
    POSITIVE LOGITS
     données
    0.08
     bio
    0.07
    arov
    0.07
    .cx
    0.07
    tics
    0.07
    :class
    0.07
    ~":"
    0.07
    鸮
    0.07
     stron
    0.07
    .EventHandler
    0.07
    Activations Density 0.324%

    No Known Activations