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. 87217
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     preserve
    -0.08
    油
    -0.07
    举措
    -0.07
    yme
    -0.07
     tales
    -0.07
    .DoesNotExist
    -0.07
    Ự
    -0.07
     referrals
    -0.07
    堎
    -0.07
     garn
    -0.07
    POSITIVE LOGITS
    gebung
    0.08
    玩家们
    0.07
    SEQU
    0.07
    皇帝
    0.07
    pter
    0.07
    TextBox
    0.07
    Ḫ
    0.07
     따른
    0.07
    ꒪
    0.06
    党和
    0.06
    Activations Density 0.001%

    No Known Activations