© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 44350
    Prev
    Next
    INDEX
    Explanations

    provide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mouth
    -0.07
    byss
    -0.07
    磹
    -0.07
    sı
    -0.07
    뵐
    -0.07
     Gamb
    -0.07
    췰
    -0.07
     yak
    -0.07
    ᡡ
    -0.07
    wagon
    -0.06
    POSITIVE LOGITS
    _SUBJECT
    0.08
    فع
    0.08
    揭开
    0.07
    至此
    0.07
     góc
    0.07
    PREC
    0.07
    ậy
    0.07
    .authenticate
    0.07
    _topology
    0.07
    .comp
    0.07
    Activations Density 0.034%

    No Known Activations