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. 7361
    Prev
    Next
    INDEX
    Explanations

    number

    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
     Scientific
    -0.08
    jn
    -0.07
    薰
    -0.07
    irtschaft
    -0.07
    认证
    -0.06
    业
    -0.06
     dentro
    -0.06
    $
    ↵
    -0.06
    工程技术
    -0.06
    indrical
    -0.06
    POSITIVE LOGITS
    Cou
    0.07
    deaux
    0.07
    _TRA
    0.07
    _peer
    0.07
     hyp
    0.07
    _UnityEngine
    0.07
     be
    0.07
    溦
    0.06
    Attachment
    0.06
    _mapper
    0.06
    Activations Density 0.007%

    No Known Activations