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. 130470
    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
    本次交易
    -0.07
    _PB
    -0.07
    NAV
    -0.07
     LEN
    -0.07
    白马
    -0.07
     biological
    -0.07
    =>'
    -0.07
     somew
    -0.07
    ま
    -0.07
     крыш
    -0.06
    POSITIVE LOGITS
     Sense
    0.07
     revolt
    0.07
     若
    0.07
     Scalars
    0.07
    _modes
    0.06
    传承
    0.06
     ermög
    0.06
     assess
    0.06
    \System
    0.06
    菁
    0.06
    Activations Density 0.010%

    No Known Activations