Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 129881
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。www
    -0.08
    毖
    -0.07
    ladesh
    -0.07
    之力
    -0.07
     PSI
    -0.07
     unprecedented
    -0.07
    drawer
    -0.07
     finns
    -0.07
    csr
    -0.07
    书香
    -0.07
    POSITIVE LOGITS
     mate
    0.08
    #",
    0.07
    =text
    0.07
    预测
    0.07
    game
    0.07
    antis
    0.07
    tokens
    0.07
     Segment
    0.07
     Sega
    0.07
    ой
    0.07
    Activations Density 0.020%

    No Known Activations