© 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. 1666
    Prev
    Next
    INDEX
    Explanations

    negations or counterfactuals

    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
    ką
    -0.08
    castle
    -0.07
    éné
    -0.07
    にも
    -0.07
    𝐀
    -0.07
    𝑝
    -0.07
    ień
    -0.07
    .assertThat
    -0.07
    ër
    -0.07
    ɛ
    -0.06
    POSITIVE LOGITS
     dom
    0.07
    绥
    0.07
     satur
    0.07
     graduate
    0.07
     öğ
    0.07
     Dzi
    0.07
    룡
    0.07
    Authority
    0.07
     #__
    0.07
     Bry
    0.07
    Activations Density 0.022%

    No Known Activations