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. 59700
    Prev
    Next
    INDEX
    Explanations

    Because

    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
    uraa
    -0.08
    медицин
    -0.07
                                                                                                   
    -0.07
    <Edge
    -0.07
    其中有
    -0.07
    ㄓ
    -0.06
    蚪
    -0.06
    潸
    -0.06
    从严治
    -0.06
     ):
    -0.06
    POSITIVE LOGITS
    利息
    0.07
    \Service
    0.06
    骨骼
    0.06
    xca
    0.06
    nature
    0.06
    Seg
    0.06
    &gt
    0.06
    掉
    0.06
    سب
    0.06
    $string
    0.06
    Activations Density 0.005%

    No Known Activations