Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 23-RESID-POST-AA
    6. 130136
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FALSE
    -0.08
    .management
    -0.07
    えない
    -0.07
    ierce
    -0.07
    讦
    -0.07
     Cuba
    -0.07
    eko
    -0.07
    腹部
    -0.07
    _DICT
    -0.07
    三维
    -0.07
    POSITIVE LOGITS
     reiterated
    0.06
    lü
    0.06
     الوز
    0.06
     appl
    0.06
    ㊨
    0.06
    Apart
    0.06
    攽
    0.06
    消化
    0.06
    �
    0.06
    utures
    0.06
    Activations Density 0.010%

    No Known Activations