© 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. 23480
    Prev
    Next
    INDEX
    Explanations

    Inability

    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
    فناد
    -0.07
     вок
    -0.07
     Dominion
    -0.07
    صندوق
    -0.07
     adventure
    -0.07
    'E
    -0.06
    atz
    -0.06
     Promotion
    -0.06
     deductible
    -0.06
     triggering
    -0.06
    POSITIVE LOGITS
    _INLINE
    0.07
    Cla
    0.07
    إبراه
    0.07
    商户
    0.07
    Father
    0.07
    נגד
    0.07
     lay
    0.07
     Markus
    0.07
    莫名
    0.07
    TextNode
    0.07
    Activations Density 0.089%

    No Known Activations