© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 86935
    Prev
    Next
    INDEX
    Explanations

    fighter jets

    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
    教室
    -0.08
     geh
    -0.08
    Eb
    -0.07
     May
    -0.07
     Leah
    -0.07
    哏
    -0.07
     Herz
    -0.07
     dia
    -0.07
     Bravo
    -0.07
     erklärt
    -0.07
    POSITIVE LOGITS
    UTERS
    0.08
    icrous
    0.07
    等症状
    0.07
    맺
    0.07
    𝑦
    0.07
     ludicrous
    0.06
    sed
    0.06
    ⼥
    0.06
    .ADD
    0.06
    年轻
    0.06
    Activations Density 0.008%

    No Known Activations