© 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. 15-RESID-POST-AA
    11. 123353
    Prev
    Next
    INDEX
    Explanations

    Period token

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Esp
    -0.07
    プレ
    -0.07
    �
    -0.06
    ᆸ
    -0.06
    LOSS
    -0.06
    素养
    -0.06
     BEN
    -0.06
    有益
    -0.06
     nobody
    -0.06
    赞誉
    -0.06
    POSITIVE LOGITS
     MJ
    0.08
    เดอะ
    0.07
    (UnityEngine
    0.07
     junction
    0.07
     quần
    0.07
    `,`
    0.07
    涄
    0.07
    _queries
    0.07
     nguyên
    0.07
    adir
    0.06
    Activations Density 0.002%

    No Known Activations