© 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. 24854
    Prev
    Next
    INDEX
    Explanations

    open-source

    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
    .vo
    -0.07
     Sao
    -0.07
     miała
    -0.07
     phổ
    -0.06
    .ke
    -0.06
    骠
    -0.06
     periods
    -0.06
     deportation
    -0.06
     sele
    -0.06
    _gl
    -0.06
    POSITIVE LOGITS
    نشط
    0.08
    🄲
    0.08
     By
    0.08
     여러분
    0.07
    することは
    0.07
     second
    0.07
    广电
    0.07
     fiber
    0.07
     Akron
    0.07
    .Repository
    0.07
    Activations Density 0.015%

    No Known Activations