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. 25144
    Prev
    Next
    INDEX
    Explanations

    Dates and anniversaries

    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
     Developer
    -0.07
     данным
    -0.07
    ountains
    -0.07
    kończ
    -0.07
    ں
    -0.07
    ѫ
    -0.07
    𝓲
    -0.06
     SDLK
    -0.06
    jax
    -0.06
     ک
    -0.06
    POSITIVE LOGITS
     soften
    0.06
     fung
    0.06
     생
    0.06
    �
    0.06
    ⏰
    0.06
    示意
    0.06
     warped
    0.06
     директор
    0.06
    BV
    0.06
    ryn
    0.06
    Activations Density 0.060%

    No Known Activations