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. 25049
    Prev
    Next
    INDEX
    Explanations

    boosting algorithms

    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
    #echo
    -0.07
    撤离
    -0.07
     Shakespeare
    -0.07
     Strom
    -0.07
     вели
    -0.06
    ⇩
    -0.06
     Bian
    -0.06
     diplomatic
    -0.06
     sucker
    -0.06
     Stephanie
    -0.06
    POSITIVE LOGITS
     noticing
    0.07
    .Panel
    0.07
     puppy
    0.07
    /Header
    0.07
     first
    0.07
     hurt
    0.07
    宾馆
    0.07
    ThreadId
    0.07
    ês
    0.07
    aining
    0.06
    Activations Density 0.010%

    No Known Activations