© 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. 76258
    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
    Se
    -0.07
    .codehaus
    -0.07
    част
    -0.07
    千万
    -0.07
    олж
    -0.07
    list
    -0.07
    쨈
    -0.07
    擔
    -0.07
    溷
    -0.07
    	sort
    -0.07
    POSITIVE LOGITS
    机械化
    0.08
     highways
    0.08
    _CNTL
    0.08
     Rapids
    0.07
    _row
    0.07
     kisses
    0.07
    业内人士
    0.07
     Nylon
    0.07
    搛
    0.07
    超过了
    0.07
    Activations Density 0.001%

    No Known Activations