© 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. 76771
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    in
    -0.08
    ень
    -0.07
    ect
    -0.07
    (items
    -0.07
     arch
    -0.07
     repetitive
    -0.07
    Marsh
    -0.07
    Ờ
    -0.07
    ʦ
    -0.07
    辛苦
    -0.06
    POSITIVE LOGITS
    Lemma
    0.08
    Alamat
    0.08
    รวม
    0.07
    digital
    0.07
    巴
    0.07
     skulle
    0.07
    大叔
    0.07
     livro
    0.06
    	ret
    0.06
    關於
    0.06
    Activations Density 0.284%

    No Known Activations