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. 35904
    Prev
    Next
    INDEX
    Explanations

    off

    np_max-act-logits · gemini-2.0-flash
    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
    組�
    -0.08
    zelf
    -0.07
     חוב
    -0.07
     است
    -0.07
    נשק
    -0.07
    奇纳河
    -0.07
     series
    -0.07
     melody
    -0.07
    院院士
    -0.07
    ıldı
    -0.07
    POSITIVE LOGITS
    loat
    0.08
    -frame
    0.08
    .NONE
    0.08
    FRING
    0.08
     restrained
    0.08
    服务员
    0.07
    IFIER
    0.07
    资源整合
    0.07
     fragmented
    0.07
    	priv
    0.07
    Activations Density 0.002%

    No Known Activations